© 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. 189111
    Prev
    Next
    INDEX
    Explanations

    please, home, cute, how, board, nike, power

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

    own life, glaringly obvious, maintained automatic, shipping details

    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
    Managed
    0.46
     denna
    0.46
     ఏద
    0.44
    here
    0.43
     någon
    0.43
    contest
    0.43
    })^{\
    0.42
    elekt
    0.42
    Butterfly
    0.42
    CRP
    0.42
    POSITIVE LOGITS
     Koval
    0.50
    有利于
    0.47
     aggravate
    0.46
     муниципалите
    0.45
    녓
    0.45
    સ્તુ
    0.44
    ಕ್
    0.43
    致命
    0.43
     каждому
    0.43
    əm
    0.43
    Activations Density 0.002%

    No Known Activations