© 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. 241526
    Prev
    Next
    INDEX
    Explanations

    CD, sourced, worksheets, advent, Table, Crack

    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
     vyb
    0.47
    찰
    0.47
     essais
    0.47
     alamu
    0.46
     goof
    0.45
     مره
    0.45
     unexplained
    0.45
    <unused1112>
    0.45
     hypoglycemia
    0.44
     नाकाम
    0.44
    POSITIVE LOGITS
    er
    0.52
    drift
    0.50
    isti
    0.50
    esc
    0.48
    terminate
    0.47
    ların
    0.46
    enable
    0.46
    bios
    0.46
    ong
    0.45
    iser
    0.45
    Activations Density 0.000%

    No Known Activations