© 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. 31-GEMMASCOPE-2-RES-65K
    7. 45554
    Prev
    Next
    INDEX
    Explanations

    volatility, acid, businesses, eggs

    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_31_width_65k_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
     Curse
    0.49
     wider
    0.45
     Kurds
    0.44
     a
    0.44
     iz
    0.43
     ado
    0.43
     lus
    0.42
     साबित
    0.42
     brou
    0.42
     NASA
    0.41
    POSITIVE LOGITS
    ل
    0.56
    ר
    0.55
    paddle
    0.52
    receipt
    0.50
    وندی
    0.49
    opp
    0.49
    concent
    0.47
    Johnny
    0.47
    ל
    0.47
    arci
    0.47
    Activations Density 0.005%

    No Known Activations