© 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. 146346
    Prev
    Next
    INDEX
    Explanations

    plenty of other

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

    increased expectations and technical issues

    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
    gi
    0.45
    椂
    0.45
    جاز
    0.43
     Housing
    0.42
     Finance
    0.42
    人物
    0.40
    ധാന
    0.40
    踪
    0.40
     Gigabit
    0.40
     Managed
    0.39
    POSITIVE LOGITS
     Сы
    0.55
     използва
    0.54
     cortos
    0.54
    Т
    0.54
    на
    0.52
     EXPERIENCE
    0.50
     със
    0.50
     жители
    0.49
     листья
    0.48
    О
    0.48
    Activations Density 0.000%

    No Known Activations