© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104862
    Prev
    Next
    INDEX
    Explanations

    transdermal N-[N-[5-[4-(aminoiminomethyl

    np_acts-logits-general · gemini-2.5-flash-lite

    specific chemicals, compounds, or ingredients, particularly in alcoholic beverages and pharmaceutical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly fires on longer, uncommon multi-syllable token fragments (e.g. “inthe” in “Absinthe,” “sincer” in “sincerest,” “imin” in “aminoiminomethyl,” “ousing” in “rousing,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EdgeInsets
    -1.70
    цыі
    -1.56
     limpiar
    -1.53
    ꦗ
    -1.44
    前から
    -1.44
    temu
    -1.41
     alianza
    -1.41
    ついに
    -1.40
     along
    -1.38
     schoenen
    -1.38
    POSITIVE LOGITS
     you
    1.55
    ↵↵
    1.44
    局面
    1.42
     trataba
    1.38
    You
    1.35
     будете
    1.31
     /
    1.30
    dellín
    1.30
     You
    1.30
     kurzen
    1.30
    Activations Density 0.059%

    No Known Activations