© 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. 150966
    Prev
    Next
    INDEX
    Explanations

    types of offerings or services

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

    indicating levels, importance, and complexity

    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
    у
    0.54
    어
    0.53
    appui
    0.46
    attaque
    0.44
    ilmiş
    0.44
    observation
    0.44
    жу
    0.43
    лом
    0.43
    icots
    0.43
    end
    0.43
    POSITIVE LOGITS
     kér
    0.54
     právě
    0.47
     tým
    0.46
    瑋
    0.45
     keny
    0.44
     vérit
    0.43
    玧
    0.43
    市值
    0.43
     spør
    0.43
    褴
    0.42
    Activations Density 0.001%

    No Known Activations