© 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. 143768
    Prev
    Next
    INDEX
    Explanations

    free-tailed bats or world records

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

    Okay, prediction

    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
    angkap
    0.55
     أبر
    0.54
     അതു
    0.51
     አስተ
    0.51
    差别
    0.49
     ተመሳሳይ
    0.49
    បញ្ចូល
    0.49
    讴
    0.48
    钣
    0.48
    采
    0.47
    POSITIVE LOGITS
     notebooks
    0.41
     chairmanship
    0.41
     interferometer
    0.41
    0.40
    ı
    0.40
    bage
    0.40
     fittings
    0.39
    IX
    0.38
     fatigue
    0.38
     expiry
    0.38
    Activations Density 0.000%

    No Known Activations