© 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. 114360
    Prev
    Next
    INDEX
    Explanations

    describing actions or states

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

    configuration elements

    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
     schwier
    0.47
     figuras
    0.45
     Chứng
    0.45
     saturation
    0.45
    耘
    0.45
     crucible
    0.44
    ாவை
    0.44
     materiais
    0.43
     Figura
    0.43
    ။
    0.43
    POSITIVE LOGITS
    lr
    0.53
    ANA
    0.50
    z
    0.50
    Officers
    0.47
    gh
    0.46
    kd
    0.46
    ž
    0.46
    kha
    0.45
    zte
    0.45
    umela
    0.44
    Activations Density 0.002%

    No Known Activations