© 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. 3796
    Prev
    Next
    INDEX
    Explanations

    code documentation analysis

    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
    Not in Any Lists

    No Comments

    Negative Logits
    igence
    3.33
    raciones
    2.69
    ला
    2.68
    QWidget
    2.66
    ेशन
    2.62
    萏
    2.58
    IGENCE
    2.57
    िला
    2.52
    íes
    2.47
    ellten
    2.46
    POSITIVE LOGITS
     pry
    2.68
    𝘨
    2.48
     st
    2.44
    BarStyle
    2.44
    cing
    2.42
    𝘴
    2.41
    arma
    2.32
    腺
    2.30
    た
    2.30
    षु
    2.28
    Activations Density 0.144%

    No Known Activations