© 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. 205972
    Prev
    Next
    INDEX
    Explanations

    mentioning Clark

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

    describing creative outlets

    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
    tudo
    0.54
    ஏ
    0.53
    ИН
    0.51
    Endereco
    0.50
    ז
    0.50
    ВС
    0.50
    ेडकर
    0.50
    ס
    0.49
    दु
    0.49
    ก
    0.49
    POSITIVE LOGITS
    :
    0.59
     is
    0.59
     Clark
    0.58
     des
    0.54
     child
    0.53
     vehicle
    0.52
     calcium
    0.52
     向
    0.52
     voltage
    0.51
     về
    0.51
    Activations Density 0.000%

    No Known Activations