© 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. 162807
    Prev
    Next
    INDEX
    Explanations

    cross-lingual identifiers

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

    Western Disturbances

    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
    from
    0.50
    专注于
    0.47
    Recent
    0.46
    שית
    0.45
     conversion
    0.45
     regulator
    0.44
    ?}",
    0.44
     harb
    0.44
    近期
    0.43
    ρων
    0.43
    POSITIVE LOGITS
     alluvial
    0.48
    ය
    0.48
    цу
    0.48
     مجموع
    0.47
    ttier
    0.46
     প্রসিদ্ধ
    0.45
    ta
    0.44
    点セット
    0.44
     کل
    0.44
    地の
    0.43
    Activations Density 0.000%

    No Known Activations