© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 247607
    Prev
    Next
    INDEX
    Explanations

    you want

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ادم
    0.45
    カウン
    0.44
    usermodel
    0.44
    적으로
    0.44
     homecoming
    0.43
    african
    0.42
     renovating
    0.42
    ཉ
    0.42
     Prostate
    0.42
    מיד
    0.41
    POSITIVE LOGITS
     និង
    0.47
     والاست
    0.47
    ق
    0.47
     maniera
    0.47
     线
    0.47
     emphas
    0.46
     rendszer
    0.45
     እንዴት
    0.45
    不下
    0.45
     famed
    0.44
    Activations Density 0.002%

    No Known Activations