© 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. 131539
    Prev
    Next
    INDEX
    Explanations

    deadline, animals, temperature, list, children

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

    connecting inputs or status

    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
     negó
    0.56
     Pilates
    0.53
     φα
    0.47
     matriline
    0.47
     прогу
    0.47
    跎
    0.47
     negar
    0.47
     físico
    0.46
     psicol
    0.46
     Sauvignon
    0.46
    POSITIVE LOGITS
    ınız
    0.47
    jdbcType
    0.47
    hype
    0.46
    bindings
    0.45
    üst
    0.45
    ப்பட
    0.44
    brackets
    0.44
    센
    0.44
    터
    0.43
    šit
    0.43
    Activations Density 0.000%

    No Known Activations