© 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. 46797
    Prev
    Next
    INDEX
    Explanations

    increasing number

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

    storage space awareness

    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
    ualmente
    0.59
    ceği
    0.53
     Frankfort
    0.50
     والذي
    0.48
     unchanged
    0.47
    éfonos
    0.47
     Eski
    0.47
     \{
    0.46
     イエロー
    0.46
     ఎ
    0.45
    POSITIVE LOGITS
     sexism
    0.49
    接続
    0.48
    眾
    0.46
    條件
    0.46
    語
    0.46
    團隊
    0.46
     fetish
    0.45
     buss
    0.45
    膚
    0.44
    艱
    0.44
    Activations Density 0.001%

    No Known Activations