© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 86784
    Prev
    Next
    INDEX
    Explanations

    chlamydia, ice, paper, cameras, oxo, allocated

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

    technical or scientific terms in academic or technical contexts.

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

    The neuron selectively activates on longer, multi-syllable content words—especially technical or compound terms.

    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
     but
    -1.65
    ibilidade
    -1.38
    Doesn
    -1.26
    [+]
    -1.21
     one
    -1.20
    icycle
    -1.16
    брь
    -1.16
     окно
    -1.16
    роза
    -1.15
    wały
    -1.14
    POSITIVE LOGITS
     ungefär
    1.61
     lära
    1.48
     سایر
    1.45
    などと
    1.42
    si
    1.38
     ujedno
    1.31
     nästan
    1.27
     едва
    1.25
    稣
    1.24
     ersten
    1.23
    Activations Density 0.124%

    No Known Activations