© 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. 217122
    Prev
    Next
    INDEX
    Explanations

    size, quantity, or progress

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

    location and description details

    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
    MED
    0.50
    PROVIDER
    0.48
    Cir
    0.46
     sağlam
    0.46
     ಏ
    0.46
    스테
    0.45
     ઊ
    0.45
    CTA
    0.44
    셍
    0.44
     गी
    0.43
    POSITIVE LOGITS
     tes
    0.56
     tess
    0.52
    ما
    0.46
    ार्टमेंट
    0.46
     municipal
    0.46
    mnopqrst
    0.46
    pt
    0.46
     forfeited
    0.45
     pard
    0.44
    pard
    0.44
    Activations Density 0.001%

    No Known Activations