© 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. 97658
    Prev
    Next
    INDEX
    Explanations

    percentages and proportions

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

    hash and combine functions

    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
    槽
    0.46
    浏览
    0.44
    條
    0.42
    Editable
    0.41
    颁
    0.41
    Flag
    0.41
    柔软
    0.41
    󠁣
    0.40
    CodeAttribute
    0.40
    像
    0.39
    POSITIVE LOGITS
    esen
    0.50
    ister
    0.49
    ana
    0.48
    ே
    0.48
    ze
    0.48
    il
    0.47
    z
    0.45
     చెప్పారు
    0.44
    ate
    0.44
    azione
    0.43
    Activations Density 0.000%

    No Known Activations