© 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. 26007
    Prev
    Next
    INDEX
    Explanations

    before your travel

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

    programming language detection

    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
    当地
    0.55
    ;
    0.54
    钀
    0.48
    ยน
    0.48
    =
    0.46
    谊
    0.46
    tsch
    0.46
    及
    0.46
    锃
    0.46
    yiz
    0.46
    POSITIVE LOGITS
     electrocardi
    0.48
    Southeast
    0.46
    inside
    0.45
     hemorrhage
    0.45
    ექტ
    0.45
    hydraulic
    0.45
     రక్త
    0.45
    performs
    0.44
    waveform
    0.44
    httpRequest
    0.42
    Activations Density 0.001%

    No Known Activations