© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10284
    Prev
    Next
    INDEX
    Explanations

    Halloween party and costumes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ы
    2.81
    KURZBESCHREIBUNG
    2.79
     painstaking
    2.75
     erros
    2.68
     erro
    2.65
     intervalos
    2.64
    Peripheral
    2.63
     reclama
    2.63
    ಕ್
    2.62
    деа
    2.61
    POSITIVE LOGITS
    e
    2.49
    i
    2.08
     Top
    1.87
     부여
    1.86
    이드
    1.81
    <h2>
    1.78
    ه
    1.77
    aer
    1.76
    le
    1.76
    زان
    1.76
    Activations Density 0.008%

    No Known Activations