© 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. 143206
    Prev
    Next
    INDEX
    Explanations

    property descriptions

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

    recap APIs

    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
     hitter
    0.46
     why
    0.45
    為什麼
    0.44
     le
    0.41
     generate
    0.40
    存
    0.39
    phantom
    0.39
     {
    0.38
     psycho
    0.38
     penet
    0.38
    POSITIVE LOGITS
    सरकारी
    0.50
     Jayne
    0.47
     Escobar
    0.47
     مارچ
    0.46
    Administrative
    0.45
    Há
    0.45
    January
    0.44
     tireless
    0.44
    ப்ர
    0.44
     Inoue
    0.44
    Activations Density 1.167%

    No Known Activations