© 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. 180634
    Prev
    Next
    INDEX
    Explanations

    established correlations, minimalist roots

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

    latex and mathematical formulas

    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
    与
    0.45
    为
    0.45
    为了
    0.44
    从
    0.43
    旧
    0.42
    当
    0.41
    áu
    0.41
     autonomía
    0.40
    让
    0.39
    ታ
    0.39
    POSITIVE LOGITS
     नहीं
    0.51
    primary
    0.50
    on
    0.49
    et
    0.49
    el
    0.49
     የበለጠ
    0.49
    ❔
    0.49
    rill
    0.48
    ActionButton
    0.48
     ます
    0.48
    Activations Density 0.000%

    No Known Activations