© 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-16K
    7. 12552
    Prev
    Next
    INDEX
    Explanations

    navigation links or titles

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

    alternate wet and dry ingredients

    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_16k_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
     ampl
    0.51
    يج
    0.51
    يق
    0.50
     melan
    0.49
     homolog
    0.48
     Tyr
    0.48
    ل
    0.48
    ي
    0.48
     وأ
    0.48
     olig
    0.48
    POSITIVE LOGITS
    ]):
    0.45
     readonly
    0.45
    ・・・。
    0.45
     رکھتے
    0.42
    inas
    0.42
    ++)
    0.42
    dotto
    0.41
    さすが
    0.41
     생긴
    0.41
    statistics
    0.41
    Activations Density 0.002%

    No Known Activations