© 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. 123905
    Prev
    Next
    INDEX
    Explanations

    label, mark, apparent, faith

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

    reservations and next questions

    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
    Negative Logits
    databind
    0.48
    ivalence
    0.47
    чик
    0.47
    чика
    0.46
    ecimiento
    0.46
     যাব
    0.46
    ículo
    0.46
    "]])
    0.45
    acu
    0.44
    vaise
    0.44
    POSITIVE LOGITS
    コ
    0.52
    ق
    0.49
     pedig
    0.48
     Guides
    0.47
    Guides
    0.46
     Rabat
    0.45
    メ
    0.44
     Italy
    0.44
    ب
    0.44
    ジュ
    0.43
    Activations Density 0.000%

    No Known Activations