© 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. 187882
    Prev
    Next
    INDEX
    Explanations

    state or description followed by specific item

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

    returning dependent video

    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
    waard
    0.57
    দোষ
    0.49
     ক্রে
    0.47
    owsky
    0.47
    学生
    0.46
    ówka
    0.46
     млад
    0.45
    诤
    0.45
    িন
    0.45
     rozwią
    0.45
    POSITIVE LOGITS
    HX
    0.50
     encompass
    0.50
    वियस
    0.47
    Spending
    0.46
    ^{\
    0.45
    }^{(
    0.44
     insanlar
    0.44
     Biochim
    0.43
     Spending
    0.43
    ουν
    0.43
    Activations Density 0.001%

    No Known Activations