© 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. 234363
    Prev
    Next
    INDEX
    Explanations

    close entrants cell cheap streptococci

    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
     בן
    0.50
     సాం
    0.48
    ן
    0.46
    ધુ
    0.45
    ین
    0.45
     LikeLike
    0.45
    मराह
    0.45
    ק
    0.45
    トライ
    0.44
    તર
    0.44
    POSITIVE LOGITS
    ኛው
    0.46
    czę
    0.46
     Pulmonary
    0.45
     pulmonary
    0.43
    lect
    0.42
     размеры
    0.42
    ”
    0.42
    heden
    0.42
    formaldehyde
    0.42
     lecteur
    0.41
    Activations Density 0.000%

    No Known Activations