© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9333
    Prev
    Next
    INDEX
    Explanations

    URLs and specific organizations

    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_22_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
     மீட்ட
    1.31
    య
    1.23
     ஈர
    1.21
     Simons
    1.20
     Siz
    1.19
     Sikk
    1.18
     Pfaff
    1.17
    땡
    1.16
     Payton
    1.16
    యన
    1.16
    POSITIVE LOGITS
    nte
    1.40
    arke
    1.33
    lde
    1.33
    UTE
    1.33
    Dale
    1.32
    ane
    1.32
     Rowe
    1.31
    ALE
    1.31
    CCE
    1.30
    ale
    1.30
    Activations Density 1.965%

    No Known Activations