© 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. 220268
    Prev
    Next
    INDEX
    Explanations

    rental terms and conditions

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

    delete logs, regulate, airflow, passes

    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
     oggetti
    0.50
     Geografia
    0.49
     of
    0.47
     in
    0.46
    ）,
    0.45
     regiões
    0.45
    (
    0.45
     gelang
    0.45
     DIE
    0.44
    quez
    0.44
    POSITIVE LOGITS
    PURE
    0.47
    ллин
    0.47
    фель
    0.45
    margin
    0.44
    preferences
    0.43
    घव
    0.43
    न्थ
    0.43
     थांब
    0.43
    TOO
    0.43
    놉
    0.42
    Activations Density 0.001%

    No Known Activations