© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 65685
    Prev
    Next
    INDEX
    Explanations

    inputenc and encoding issues

    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
     libr
    0.49
    는
    0.49
    зап
    0.48
     metamorphic
    0.48
    љ
    0.48
    л
    0.47
    вых
    0.46
    ω
    0.46
     metab
    0.46
    ках
    0.45
    POSITIVE LOGITS
    attle
    0.52
    unken
    0.51
     दृढ़
    0.51
     مختلفة
    0.46
    cribes
    0.46
    unehm
    0.46
    raient
    0.46
    髡
    0.46
    ere
    0.46
    sembles
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.