© 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. 245258
    Prev
    Next
    INDEX
    Explanations

    common inanimate allergens from

    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
    Ad
    0.52
    پ
    0.51
    B
    0.51
    BAN
    0.50
    PY
    0.50
    PIN
    0.50
    Em
    0.49
    EFFECT
    0.48
     સારી
    0.48
    P
    0.48
    POSITIVE LOGITS
     artisanal
    0.58
     custos
    0.55
     gathering
    0.54
     artisan
    0.52
     detonation
    0.52
     cytoplasmic
    0.51
     door
    0.51
     compilation
    0.51
     goalt
    0.51
     deleting
    0.50
    Activations Density 0.000%

    No Known Activations