© 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. 3791
    Prev
    Next
    INDEX
    Explanations

    which introduces explanation

    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
    šet
    2.56
    𝕚
    2.54
    iss
    2.46
    au
    2.43
    isać
    2.29
    uts
    2.21
    𝕖
    2.21
    zok
    2.18
    sklär
    2.17
    šan
    2.16
    POSITIVE LOGITS
    𝒐
    3.57
    𝒆
    3.50
     |”
    3.16
    MyToolkit
    3.05
     pasa
    2.98
    𝒕
    2.97
    𝒚
    2.96
     gobier
    2.95
    מין
    2.95
    EF
    2.88
    Activations Density 0.051%

    No Known Activations