© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106438
    Prev
    Next
    INDEX
    Explanations

    near apartment

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

    The neuron is keyed to structural list and section markers—e.g. bullets, numbered or parenthesized items, and heading‐style tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    కో
    -0.97
     Soporte
    -0.91
     Opiniones
    -0.91
     Diseño
    -0.89
    っていましたが
    -0.86
     RelativeLayout
    -0.86
    posY
    -0.84
     oferty
    -0.82
    Flammability
    -0.82
    бка
    -0.82
    POSITIVE LOGITS
     near
    1.09
     unmittel
    1.03
     매우
    0.98
     very
    0.93
     Huge
    0.90
     дуже
    0.90
     fully
    0.90
     Very
    0.88
     facing
    0.88
     向け
    0.88
    Activations Density 0.002%

    No Known Activations