© 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. 3924
    Prev
    Next
    INDEX
    Explanations

    insert values

    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
    ni
    1.57
    iversity
    1.49
    dem
    1.46
    roadmap
    1.38
    speakers
    1.36
    ně
    1.36
    ním
    1.34
    媧
    1.32
    nu
    1.31
    ny
    1.29
    POSITIVE LOGITS
    此之外
    1.72
    MENTS
    1.65
     nieve
    1.61
    LOADING
    1.58
    quele
    1.58
    INGS
    1.56
    靂
    1.54
    𝒍
    1.51
    LEADING
    1.51
    Methoxy
    1.50
    Activations Density 0.065%

    No Known Activations