© 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. 4536
    Prev
    Next
    INDEX
    Explanations

    percentage of these

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

    graphics driver, audio file, open directories

    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
    ’
    0.57
    -
    0.56
    tt
    0.52
    ss
    0.50
    $
    0.50
    ↵
    0.50
     Be
    0.50
    тация
    0.49
     Trans
    0.49
    Week
    0.46
    POSITIVE LOGITS
     polypeptides
    0.54
     рекомен
    0.52
     solubilities
    0.52
     የወ
    0.50
    pOt
    0.50
    āb
    0.50
     homologs
    0.50
     químicos
    0.49
    𒋼
    0.49
     หย
    0.49
    Activations Density 0.000%

    No Known Activations