© 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. 220788
    Prev
    Next
    INDEX
    Explanations

    quantifying or listing items

    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
    ennies
    0.44
    梳
    0.39
    💸
    0.38
     digits
    0.38
     cryptocur
    0.38
     blockchain
    0.37
    也就是
    0.35
    碍
    0.35
    区块链
    0.34
     irgende
    0.34
    POSITIVE LOGITS
    ?";
    0.39
     साब
    0.39
     ?";
    0.38
     इस्ती
    0.36
     memas
    0.36
     جاتی
    0.36
     dossiers
    0.36
    gast
    0.35
     TUR
    0.35
     turista
    0.35
    Activations Density 0.005%

    No Known Activations