© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 227470
    Prev
    Next
    INDEX
    Explanations

    food preparation and ingredients

    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
    Bel
    0.50
    线条
    0.47
     bel
    0.46
    ण्ड
    0.45
    Append
    0.45
     بسته
    0.44
     Bel
    0.44
    ظ
    0.42
     Parties
    0.42
    Someone
    0.42
    POSITIVE LOGITS
     newly
    0.48
    intendent
    0.48
    aceutical
    0.48
    ৬০
    0.47
    verse
    0.46
     wasnt
    0.46
    ດ້
    0.46
    🏥
    0.46
    гів
    0.45
     secreted
    0.45
    Activations Density 0.000%

    No Known Activations