© 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. 151024
    Prev
    Next
    INDEX
    Explanations

    company names and roles

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

    conceptually simple

    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
    пки
    0.45
    ель
    0.45
    ppler
    0.44
    賭
    0.44
     университета
    0.44
    每年
    0.42
    рко
    0.42
    ка
    0.41
    睪
    0.41
    樹
    0.41
    POSITIVE LOGITS
     linéaire
    0.54
    یم
    0.52
     président
    0.50
     uomini
    0.50
    ność
    0.49
     étudi
    0.49
    ivité
    0.47
     علی
    0.46
     retains
    0.46
     ViewData
    0.45
    Activations Density 0.000%

    No Known Activations