© 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. 106177
    Prev
    Next
    INDEX
    Explanations

    money, units, name, relation, computer, lists

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

    growth potential

    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
     Hrvatskoj
    0.47
    谁
    0.46
    شاعرانه
    0.46
    你也
    0.45
     errand
    0.45
     direcciones
    0.45
     {}>,
    0.45
    ქვთ
    0.44
    "。
    0.44
    ':
    0.44
    POSITIVE LOGITS
    as
    0.48
    ool
    0.47
    oS
    0.47
     моло
    0.46
    Mir
    0.45
     মোল
    0.44
    on
    0.44
    multicolumn
    0.44
    Started
    0.44
    lüssel
    0.44
    Activations Density 0.001%

    No Known Activations