© 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. 3975
    Prev
    Next
    INDEX
    Explanations

    my AI characteristics

    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
    OT
    2.80
    yama
    2.67
    ውን
    2.57
    bibliothek
    2.42
    ()`
    2.41
    क्षात्कार
    2.39
     "--
    2.33
    ング
    2.33
    ymmetric
    2.33
    yez
    2.32
    POSITIVE LOGITS
    ྕ
    2.63
     săn
    2.62
     pobl
    2.56
    ly
    2.48
    }}$$
    2.44
     rive
    2.41
     Trunk
    2.38
    StdHandle
    2.35
    rung
    2.34
    রার
    2.33
    Activations Density 0.092%

    No Known Activations