© 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. 212777
    Prev
    Next
    INDEX
    Explanations

    with special / no need

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

    current consensus

    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
    ರುತ್ತವೆ
    0.60
     RULES
    0.47
    НК
    0.46
     duckys
    0.46
     yells
    0.44
    惴
    0.44
     puns
    0.44
     unhealthy
    0.43
     प्रश्‍
    0.43
     egregious
    0.43
    POSITIVE LOGITS
     Management
    0.52
     Set
    0.51
     प्रबंधन
    0.45
    }/
    0.45
     Managing
    0.44
    toContain
    0.44
     Diver
    0.44
     ²
    0.44
    à
    0.43
    ുകൊ
    0.43
    Activations Density 0.000%

    No Known Activations