© 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. 111372
    Prev
    Next
    INDEX
    Explanations

    market analyzer touchpad

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

    breakdown, tokenize

    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
     vzh
    0.46
    替
    0.46
     glau
    0.43
    otonic
    0.42
     ロゴ
    0.42
     définitive
    0.41
     library
    0.41
     第
    0.41
     ch
    0.41
     однозна
    0.41
    POSITIVE LOGITS
    ইন
    0.46
     Lightweight
    0.44
     ছিন
    0.44
    お金
    0.44
    GetLength
    0.44
     Başkan
    0.44
    Blocked
    0.43
     Trained
    0.42
     Commissioners
    0.41
     Sunlight
    0.41
    Activations Density 0.002%

    No Known Activations