© 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. 221571
    Prev
    Next
    INDEX
    Explanations

    performance comparison

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

    electoral college vote

    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
     قاب
    0.46
     defender
    0.44
    蟳
    0.43
     tamar
    0.43
     aq
    0.43
     thanked
    0.43
    డింది
    0.42
     صلاحیت
    0.42
     حنا
    0.42
     الإسلام
    0.42
    POSITIVE LOGITS
    ρε
    0.50
    ਿਕ
    0.50
    み
    0.47
    I
    0.46
    ția
    0.46
    বে
    0.45
    ロード
    0.45
    льта
    0.44
    द
    0.44
    債
    0.44
    Activations Density 0.000%

    No Known Activations