© 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. 222151
    Prev
    Next
    INDEX
    Explanations

    dumpster on the street

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

    usage, successful, version, Out, firms

    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
     materiál
    0.46
     nonlinear
    0.46
     cadastro
    0.46
     chained
    0.46
     gemstones
    0.46
     ♡
    0.45
     ebook
    0.44
     aesthetic
    0.44
     nữ
    0.44
     hijab
    0.43
    POSITIVE LOGITS
    恒
    0.46
    Tele
    0.45
    했고
    0.45
    Chairman
    0.44
    Ic
    0.43
    gment
    0.42
     telep
    0.42
    Edge
    0.42
    ലീസ്
    0.42
    Track
    0.42
    Activations Density 0.002%

    No Known Activations