© 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. 194853
    Prev
    Next
    INDEX
    Explanations

    discarding, bake, Sergio, his, vendors

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

    code punctuation and separators

    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
    ర
    0.50
    swear
    0.48
     Admittedly
    0.48
    services
    0.47
    serialization
    0.47
    venues
    0.47
    submissions
    0.46
    processors
    0.46
    snacks
    0.46
     الغذ
    0.45
    POSITIVE LOGITS
     pop
    0.54
     popped
    0.51
     j
    0.50
     greek
    0.50
     J
    0.49
     interior
    0.49
     anarch
    0.49
     explode
    0.49
     propane
    0.47
     govern
    0.47
    Activations Density 0.001%

    No Known Activations