© 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. 104253
    Prev
    Next
    INDEX
    Explanations

    Kentucky Proud, not distrust

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

    exploring ideas, these issues, inspired by

    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
    stit
    0.51
     piercing
    0.51
    വൃത്തി
    0.50
     pungent
    0.50
    黐
    0.49
     लाख
    0.49
    بری
    0.48
     भय
    0.47
    ovaniyu
    0.47
     त्याची
    0.46
    POSITIVE LOGITS
    _
    0.59
    ^
    0.55
    =(
    0.55
    +
    0.54
    /
    0.52
     ^
    0.48
    সমূহ
    0.47
    -
    0.45
    $,
    0.45
    )^
    0.45
    Activations Density 0.001%

    No Known Activations