© 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. 2661
    Prev
    Next
    INDEX
    Explanations

    person who

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

    technical components

    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
    人
    0.50
    нул
    0.46
    ные
    0.46
     privacidad
    0.46
    ociação
    0.43
    ưng
    0.43
     opacity
    0.43
    THz
    0.43
    <0x80>
    0.41
    orescence
    0.41
    POSITIVE LOGITS
     THOMAS
    0.55
     ब्रै
    0.54
     revising
    0.52
     FACTORS
    0.51
    allist
    0.50
     settimana
    0.50
     เฮ
    0.50
     revised
    0.49
     ILLUSTR
    0.49
    ができる
    0.48
    Activations Density 0.000%

    No Known Activations