© 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. 197599
    Prev
    Next
    INDEX
    Explanations

    custom, nationalities, mainland, apk, subject, one, supplied, partner

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

    code generation or capability

    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
     erro
    0.49
     thẩm
    0.49
     ಸ್ನೇ
    0.47
     যথ
    0.47
    ית
    0.45
     آئینہ
    0.45
     buccal
    0.44
    鑾
    0.43
     كوساين
    0.43
     تصير
    0.43
    POSITIVE LOGITS
    xe
    0.54
    ells
    0.48
    fieldName
    0.48
    campaign
    0.47
    onClick
    0.47
    laws
    0.46
    olver
    0.46
    PROGRAM
    0.46
    array
    0.46
    olen
    0.46
    Activations Density 0.000%

    No Known Activations