© 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. 1325
    Prev
    Next
    INDEX
    Explanations

    product names and associated types

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

    mentioning models and names

    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
     цей
    0.29
     വിവിധ
    0.29
     ஐந்து
    0.28
    𐰢
    0.28
     திரை
    0.28
     международного
    0.28
     wszel
    0.28
     დიდი
    0.28
    üksek
    0.27
     сельскохозяй
    0.27
    POSITIVE LOGITS
    +
    0.37
    -
    0.36
    /
    0.33
    .
    0.32
    -/
    0.29
     but
    0.29
    "
    0.29
    :
    0.29
    '
    0.29
    ",
    0.28
    Activations Density 0.177%

    No Known Activations