© 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. 20884
    Prev
    Next
    INDEX
    Explanations

    code structures and function calls

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

    code structures and parameters

    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
     Anzahl
    0.42
     நிறைய
    0.42
    \}=
    0.41
    Improved
    0.41
     Lösungen
    0.41
     জ্বর
    0.41
     ﺍ
    0.40
    Cultural
    0.39
    ந்தார்
    0.39
     ڕۆ
    0.39
    POSITIVE LOGITS
    ({
    0.52
    ,{
    0.47
     {
    0.46
     ({
    0.46
    ',{
    0.43
    goals
    0.40
    ({})
    0.39
     goals
    0.38
    vr
    0.38
    fa
    0.37
    Activations Density 0.000%

    No Known Activations