© 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. 186538
    Prev
    Next
    INDEX
    Explanations

    defining actions and outcomes

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

    explaining code or writing

    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
    führt
    0.54
    冫
    0.51
    ście
    0.50
    wości
    0.50
    ̢
    0.49
    ..?
    0.48
    ynı
    0.47
    ؟!
    0.47
    istič
    0.47
    !<
    0.47
    POSITIVE LOGITS
     breeders
    0.59
     elucidate
    0.46
     داد
    0.45
     breeder
    0.44
     عندهم
    0.44
     acá
    0.42
     prosecutions
    0.42
    NUMBER
    0.42
     opcode
    0.41
     raies
    0.41
    Activations Density 0.001%

    No Known Activations