© 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. 211266
    Prev
    Next
    INDEX
    Explanations

    high cost, risk, or toxicity

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

    complex technical writing

    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
    -
    0.54
    Store
    0.47
     populated
    0.46
    Rating
    0.46
    EV
    0.45
    ící
    0.45
     rating
    0.45
    C
    0.45
     yard
    0.45
    underbrace
    0.43
    POSITIVE LOGITS
     وبر
    0.53
     کامیاب
    0.53
     Chayin
    0.51
    保温
    0.49
    쫌
    0.49
    ျ
    0.49
     কক্স
    0.48
     Gameplay
    0.48
    चलित
    0.48
     notizia
    0.47
    Activations Density 0.001%

    No Known Activations