© 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. 34-GEMMASCOPE-RES-131K
    7. 107166
    Prev
    Next
    INDEX
    Explanations

    court heard

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     jis
    -0.82
    太好了
    -0.75
    回答
    -0.73
     incipient
    -0.71
     and
    -0.71
    zcan
    -0.71
    mittags
    -0.70
     справи
    -0.69
     ура
    -0.69
     agi
    -0.68
    POSITIVE LOGITS
     heard
    2.91
    heard
    2.02
     hear
    2.02
     hearing
    1.90
     hears
    1.81
    Heard
    1.52
     Heard
    1.52
     Hearing
    1.27
     entendu
    1.27
    hearing
    1.25
    Activations Density 0.015%

    No Known Activations