© 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. 200580
    Prev
    Next
    INDEX
    Explanations

    infer, December, movie, creative, for

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

    Australia between game index Access spine but manifest taken away

    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
    t
    0.54
    y
    0.52
     goc
    0.49
     Started
    0.48
    h
    0.45
    q
    0.44
    u
    0.43
    XMLHttpRequest
    0.43
    mock
    0.42
     pies
    0.42
    POSITIVE LOGITS
    㝅
    0.48
     ఇతర
    0.48
     करिकुलम
    0.48
    Endereco
    0.47
    สนับสนุน
    0.46
    <unused355>
    0.46
    ियों
    0.46
    ្នុង
    0.46
    㜖
    0.46
    性は
    0.45
    Activations Density 0.000%

    No Known Activations