© 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. 156002
    Prev
    Next
    INDEX
    Explanations

    value, itself, recollections

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

    foreign words, attributes

    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
     HttpClient
    0.50
    規則
    0.48
    HttpClient
    0.47
     définition
    0.46
     patent
    0.45
    <0x81>
    0.45
    ással
    0.45
     ⚫
    0.45
     သူ
    0.45
     FIR
    0.43
    POSITIVE LOGITS
    ਾਰ
    0.49
    inizio
    0.48
     않은
    0.47
     सितारों
    0.46
     estrellas
    0.46
    Dieser
    0.46
    )]),
    0.45
    ומים
    0.45
    ﺮ
    0.44
    כת
    0.42
    Activations Density 0.000%

    No Known Activations