© 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. 212522
    Prev
    Next
    INDEX
    Explanations

    lists, names, actions

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

    generating using yield

    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
    RUNTIME
    0.48
     prospective
    0.44
     Wissenschaften
    0.42
    :}
    0.42
    ться
    0.41
    Ratings
    0.41
     Keluarga
    0.40
    GALL
    0.40
    ü
    0.39
    閣
    0.39
    POSITIVE LOGITS
    ərd
    0.50
     cappuccino
    0.49
    mon
    0.48
    ેશ
    0.48
    وتي
    0.48
    ekan
    0.47
     প্রাসাদ
    0.47
    larda
    0.46
    rapper
    0.46
     fik
    0.46
    Activations Density 0.001%

    No Known Activations