© 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. 98963
    Prev
    Next
    INDEX
    Explanations

    infant carriers

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

    negotiating contracts

    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
     けど
    0.48
     accompanies
    0.44
     还
    0.44
     квіт
    0.44
     გამოი
    0.44
     型
    0.43
     carène
    0.43
     አማ
    0.43
    诩
    0.43
     donut
    0.42
    POSITIVE LOGITS
     मिलना
    0.51
    respuesta
    0.47
    ahuasca
    0.47
    urg
    0.46
    buyers
    0.46
    clubs
    0.46
    const
    0.45
    тек
    0.45
    âns
    0.45
    migrations
    0.45
    Activations Density 0.001%

    No Known Activations