© 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. 222973
    Prev
    Next
    INDEX
    Explanations

    actions and states

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

    conjunctions and choices

    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
    .。
    0.44
    。(
    0.40
    。（
    0.40
    。
    0.39
     那
    0.39
    ۔
    0.39
    。）
    0.38
    ®.
    0.38
    ။
    0.38
    噉
    0.38
    POSITIVE LOGITS
     עם
    0.45
     with
    0.44
    ನಲ್ಲಿ
    0.41
     and
    0.39
     بقى
    0.39
     dengan
    0.38
     avec
    0.38
    ceğ
    0.36
    เมื่อ
    0.34
     અને
    0.34
    Activations Density 0.140%

    No Known Activations