© 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. 178191
    Prev
    Next
    INDEX
    Explanations

    short phrases and place names

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

    abstractclasses

    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
    bpmOb
    0.47
     簡単
    0.47
    ఎస్
    0.46
    <unused82>
    0.45
     определение
    0.44
    ्यूशन
    0.43
     คูณ
    0.43
     ながら
    0.43
    <unused693>
    0.43
    為何
    0.42
    POSITIVE LOGITS
    y
    0.54
     Bytes
    0.50
    k
    0.48
     Nature
    0.48
    Bytes
    0.46
     fej
    0.46
    SUM
    0.46
    Pixels
    0.45
    Days
    0.45
    p
    0.45
    Activations Density 0.002%

    No Known Activations