© 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. 89383
    Prev
    Next
    INDEX
    Explanations

    Artist Directory

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

    individual, many languages, wind, ransomware

    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
    መሪያ
    0.57
    system
    0.52
     CA
    0.47
     decade
    0.46
     ant
    0.46
     правила
    0.46
    ϻ
    0.45
    !/"
    0.45
     tránh
    0.44
    ล่าสุด
    0.44
    POSITIVE LOGITS
    問い
    0.55
     बात
    0.47
    Ｗ
    0.45
     llamadas
    0.45
    叫
    0.45
    畩
    0.44
    राब
    0.44
    룻
    0.44
     Gobierno
    0.43
    оти
    0.43
    Activations Density 0.000%

    No Known Activations