© 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. 75109
    Prev
    Next
    INDEX
    Explanations

    contract between

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

    offering paths, social factors

    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
     landlab
    0.54
     ሶ
    0.54
    ತ್ಮ
    0.51
    ෆ
    0.50
    聑
    0.50
    ။
    0.50
     ތ
    0.49
    ৤
    0.49
    圤
    0.49
    の中で
    0.48
    POSITIVE LOGITS
    b
    0.46
    p
    0.45
    ští
    0.44
    waiting
    0.44
    EL
    0.43
    deutscher
    0.43
    ield
    0.43
    glut
    0.43
    ž
    0.42
    part
    0.42
    Activations Density 0.000%

    No Known Activations