© 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. 109015
    Prev
    Next
    INDEX
    Explanations

    stock, treasury, company, country

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

    around town

    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
    俟
    0.53
    س
    0.50
     errors
    0.50
     error
    0.47
    ق
    0.47
     resultat
    0.46
     to
    0.45
     Layers
    0.45
     serii
    0.45
     Tage
    0.44
    POSITIVE LOGITS
    facing
    0.48
    ังสือ
    0.46
    जफ्
    0.46
    लन
    0.45
    ഴ്‌
    0.45
    ৬০
    0.44
     (#{
    0.44
    $)$.
    0.44
    லாமல்
    0.43
    furnished
    0.43
    Activations Density 0.000%

    No Known Activations