© 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. 72338
    Prev
    Next
    INDEX
    Explanations

    event, publication, or place

    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_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
     different
    -1.16
    //!
    -1.12
    /***
    -1.10
     large
    -1.06
     ダイヤモンド
    -1.00
     particular
    -0.98
     multitude
    -0.97
     throng
    -0.95
    dă
    -0.95
    ्या
    -0.94
    POSITIVE LOGITS
     that
    1.39
    のうち
    1.31
    さすがに
    1.13
     включая
    1.01
    🚦
    1.00
     לכם
    0.99
    pleasure
    0.96
     estime
    0.95
    caref
    0.95
    uette
    0.94
    Activations Density 0.077%

    No Known Activations