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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68209
    Prev
    Next
    INDEX
    Explanations

    PTSD, connotation, NLP, cmap, uart

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

    This neuron fires on uncommon or specialized content words—particularly low-frequency terms and jargon.

    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
     standout
    -3.06
    lossians
    -2.58
     poignant
    -2.34
    ⚋
    -2.30
    是自己
    -2.27
    慥
    -2.20
    стреча
    -2.17
    הם
    -2.14
     detaylı
    -2.11
    ⃨
    -2.08
    POSITIVE LOGITS
    la
    2.95
    such
    2.70
     were
    2.69
    to
    2.69
    遢
    2.67
    e
    2.63
    ERS
    2.52
    餮
    2.45
    ча
    2.34
    ため
    2.28
    Activations Density 0.014%

    No Known Activations