© 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. 177979
    Prev
    Next
    INDEX
    Explanations

    Saturdays wisdom indicated Quick

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

    specific project focus

    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
    پل
    0.46
     effectués
    0.45
    官方
    0.44
    Elev
    0.43
     elevates
    0.43
    编
    0.42
     sắc
    0.42
    𝑒
    0.42
     dépassant
    0.42
     поднима
    0.41
    POSITIVE LOGITS
     হাইড্রোক
    0.47
     sympath
    0.45
    ince
    0.43
    achusetts
    0.42
    hedge
    0.42
     assessors
    0.41
    ेंशियल
    0.40
    ซ์
    0.40
    ляти
    0.40
    личе
    0.40
    Activations Density 0.002%

    No Known Activations