© 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. 7980
    Prev
    Next
    INDEX
    Explanations

    sound and action descriptions

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

    mention specific details

    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
     "-",
    0.48
     traceability
    0.44
     '-',
    0.42
     variances
    0.41
    ,‎
    0.41
     relevancia
    0.41
    ‌,
    0.40
     "=",
    0.40
     algorit
    0.40
     relev
    0.39
    POSITIVE LOGITS
    laughs
    0.54
    ?]
    0.52
    formerly
    0.48
    inizio
    0.47
    笑着
    0.46
    pause
    0.45
     exclaimed
    0.44
    !]
    0.43
     jokingly
    0.43
    continues
    0.42
    Activations Density 0.024%

    No Known Activations