© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 34401
    Prev
    Next
    INDEX
    Explanations

    representative sample

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

    when... different

    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
    “
    0.45
     proiz
    0.44
    🔍
    0.43
    弊社
    0.43
    CK
    0.43
    狀況
    0.43
    SPECIAL
    0.42
     operating
    0.42
     marrón
    0.42
    好評
    0.42
    POSITIVE LOGITS
     اسلح
    0.45
     तस्वी
    0.43
     હત્યા
    0.42
     なら
    0.42
     neuropath
    0.41
     linux
    0.39
     Punkte
    0.38
    )/\
    0.38
     corro
    0.38
     -----
    0.38
    Activations Density 0.000%

    No Known Activations