© 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. 3895
    Prev
    Next
    INDEX
    Explanations

    human error and evaluation

    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
    грамм
    2.47
    ylate
    2.27
    YAN
    2.25
    aue
    2.18
     ağır
    2.18
    !("{:
    2.15
    ált
    2.15
    钱
    2.14
     sím
    2.11
     errado
    2.07
    POSITIVE LOGITS
    ness
    4.15
    ity
    3.37
    ства
    3.23
    NESS
    3.23
    heid
    3.17
    idad
    2.89
    তায়
    2.79
    er
    2.76
    ತೆಯ
    2.75
    nesses
    2.75
    Activations Density 0.221%

    No Known Activations