© 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. 17134
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation separators

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

    code and return statements

    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
     ,
    0.63
     .(
    0.59
     cosi
    0.58
     !!!!
    0.57
     !!!!!
    0.51
     sony
    0.50
    !!!!!
    0.50
     bbq
    0.50
    !!!!
    0.49
     xaxis
    0.48
    POSITIVE LOGITS
    ℗
    0.52
    ⎆
    0.52
     посредством
    0.52
    ──
    0.50
    Framebuffer
    0.49
    Revision
    0.49
    över
    0.47
    abilities
    0.47
    Snake
    0.47
    ────────────────
    0.46
    Activations Density 0.021%

    No Known Activations