© 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. 26763
    Prev
    Next
    INDEX
    Explanations

    predicting future outcomes

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

    trial

    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
    changes
    0.46
     nebo
    0.46
     造
    0.45
     款
    0.44
     yerde
    0.44
     danas
    0.43
    če
    0.43
    quila
    0.43
    esimo
    0.43
    法令
    0.43
    POSITIVE LOGITS
    وسی
    0.46
     Starter
    0.45
    させて頂きます
    0.44
    錆
    0.44
     supplying
    0.44
     চালিয়ে
    0.43
    鷺
    0.43
    セックス
    0.43
     manometer
    0.43
     lumped
    0.43
    Activations Density 0.000%

    No Known Activations