© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 195804
    Prev
    Next
    INDEX
    Explanations

    non-commercial transitory

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

    measurement units and regions

    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
    াদার
    0.46
     Webin
    0.45
    アフ
    0.43
    インストール
    0.43
    これから
    0.43
    ят
    0.42
    ଆ
    0.42
    આ
    0.42
    ología
    0.41
    ஆர்
    0.41
    POSITIVE LOGITS
     neuen
    0.43
     consider
    0.43
     gaseous
    0.42
     syphilit
    0.42
     lung
    0.42
     privaten
    0.42
     eo
    0.42
     guild
    0.41
     auch
    0.41
     orang
    0.41
    Activations Density 0.000%

    No Known Activations