© 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. 125964
    Prev
    Next
    INDEX
    Explanations

    was posted

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

    understanding relevance and databases

    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
    は
    0.57
     other
    0.52
    ้
    0.52
     থাকেন
    0.50
     Xmas
    0.49
     avaient
    0.49
     jaw
    0.47
     solaire
    0.47
     Murakami
    0.47
    ating
    0.46
    POSITIVE LOGITS
    rás
    0.53
    Ր
    0.46
     названия
    0.45
    Because
    0.45
     giấy
    0.45
    ⤷
    0.45
     необходимость
    0.45
     filede
    0.45
     рост
    0.44
    矗
    0.44
    Activations Density 0.000%

    No Known Activations