© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 23882
    Prev
    Next
    INDEX
    Explanations

    declarations and attempts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,|
    0.42
    \|+\
    0.40
    REY
    0.40
     ربعه
    0.39
    aryn
    0.39
     типов
    0.39
     mistura
    0.38
    াম্প
    0.38
    គោ
    0.38
     ;{
    0.37
    POSITIVE LOGITS
    rest
    0.45
     declared
    0.42
     rest
    0.40
     Signup
    0.39
     stone
    0.38
     signup
    0.38
     UI
    0.38
     declaration
    0.38
    bral
    0.37
     declare
    0.37
    Activations Density 0.000%

    No Known Activations