© 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. 179262
    Prev
    Next
    INDEX
    Explanations

    version offeel atis effectiveexcept forthe thirdthe regionpainted spinningincome fromMBA students0 –

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

    instruction prompts

    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
    رويج
    0.54
    рии
    0.50
    раў
    0.50
     propagates
    0.49
    钀
    0.48
    jších
    0.48
    اردوش
    0.48
     propagate
    0.47
    靗
    0.46
    다고
    0.46
    POSITIVE LOGITS
    us
    0.57
     Det
    0.53
     {
    0.52
     Team
    0.51
     Tablet
    0.51
     Hotel
    0.50
    ule
    0.49
     Me
    0.48
     महाविद्यालय
    0.48
     Magistrate
    0.48
    Activations Density 0.000%

    No Known Activations