© 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. 128145
    Prev
    Next
    INDEX
    Explanations

    consequences of it

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

    actions followed by descriptions

    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
     Vel
    0.51
    a
    0.46
    er
    0.46
     Cel
    0.45
     eponymous
    0.45
    iselt
    0.45
     Adel
    0.44
     Historical
    0.44
     vel
    0.43
     Elekt
    0.43
    POSITIVE LOGITS
     移動
    0.50
     書
    0.49
     省
    0.46
     gamanam
    0.46
     ល
    0.46
    允許
    0.45
     знали
    0.45
    𝕞
    0.45
    лі
    0.44
     abbrevi
    0.44
    Activations Density 0.002%

    No Known Activations