© 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. 43710
    Prev
    Next
    INDEX
    Explanations

    legal or financial terms

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

    streaming bandwidth

    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
    o
    0.54
    n
    0.52
    it
    0.51
    abot
    0.49
     pobl
    0.48
     Romana
    0.48
    an
    0.48
    a
    0.47
    ř
    0.46
    urnal
    0.46
    POSITIVE LOGITS
     μου
    0.45
    お客様
    0.43
    Kes
    0.43
     microphones
    0.42
    線を
    0.41
     kes
    0.41
     ERIC
    0.40
     제가
    0.40
    Ι
    0.40
     ئێ
    0.39
    Activations Density 0.000%

    No Known Activations