© 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. 22-GEMMASCOPE-RES-131K
    7. 65162
    Prev
    Next
    INDEX
    Explanations

    behind or through

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

    The neuron strongly fires on words that describe physical movement or spatial relationships (e.g. behind, landed, walked, into, fired, sat, engage, connect).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     this
    -1.39
     also
    -1.07
     that
    -1.04
     también
    -1.01
    après
    -0.92
     you
    -0.89
     akhir
    -0.88
     после
    -0.87
     après
    -0.86
     after
    -0.85
    POSITIVE LOGITS
     peuples
    0.96
    まずは
    0.90
     entrando
    0.90
     посту
    0.89
     ווא
    0.87
    เข้า
    0.86
     atraves
    0.82
     Substitute
    0.82
    以内
    0.82
    وفق
    0.82
    Activations Density 0.020%

    No Known Activations