© 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. 121949
    Prev
    Next
    INDEX
    Explanations

    date, number, or list structure

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

    procrastination and ability to rights

    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
     зберіга
    0.52
     період
    0.48
     сі
    0.48
     réunis
    0.47
     féidir
    0.47
     fenced
    0.46
     behaved
    0.46
    綣
    0.46
    Ꮀ
    0.45
     Deluxe
    0.45
    POSITIVE LOGITS
    ")).
    0.46
     СМИ
    0.45
    icit
    0.45
     সঠিকভাবে
    0.44
    "+
    0.44
     ");
    0.43
    avar
    0.43
    astre
    0.43
    ۳
    0.43
    遭到
    0.42
    Activations Density 0.000%

    No Known Activations