© 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. 221913
    Prev
    Next
    INDEX
    Explanations

    website www

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

    standard input (stdin)

    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
     भैर
    0.49
    <h1>
    0.45
    effector
    0.44
     lăn
    0.44
    {"
    0.43
    एन
    0.42
    मैन
    0.41
    トラン
    0.41
    我が
    0.40
    真心
    0.40
    POSITIVE LOGITS
     droga
    0.46
     კ
    0.46
     соціа
    0.45
     Scripture
    0.44
     obsz
    0.44
     burg
    0.44
     dziecka
    0.44
     ně
    0.44
     Judiciary
    0.44
     lokalen
    0.44
    Activations Density 0.000%

    No Known Activations