© 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. 133314
    Prev
    Next
    INDEX
    Explanations

    desirable to, policy coverage, business segment

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

    even some livestock feed crops

    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
    ט
    0.56
     মানবাধিকার
    0.54
     каждый
    0.54
    iczny
    0.52
     stupidity
    0.49
     odpow
    0.49
    არი
    0.48
     বক্তব
    0.48
    哐
    0.48
     убий
    0.48
    POSITIVE LOGITS
     of
    0.49
    sche
    0.46
    ü
    0.45
    hi
    0.43
     CPR
    0.43
    golf
    0.42
    store
    0.42
    US
    0.42
    za
    0.41
    à
    0.40
    Activations Density 0.001%

    No Known Activations