© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8178
    Prev
    Next
    INDEX
    Explanations

    printing or visualizing results

    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
    -
    1.12
    ,
    1.08
     arts
    1.04
     business
    0.96
     shop
    0.95
     studio
    0.95
     hobbies
    0.92
     farm
    0.91
     academy
    0.90
     care
    0.89
    POSITIVE LOGITS
    index
    1.54
    {}'.
    1.49
    」（
    1.41
    」。
    1.38
    minimal
    1.37
    README
    1.34
    detail
    1.33
    excerpt
    1.32
    ».
    1.31
    »،
    1.29
    Activations Density 0.053%

    No Known Activations