© 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. 8453
    Prev
    Next
    INDEX
    Explanations

    actual program execution

    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
    上有
    1.03
    结束后
    0.92
     üzerine
    0.90
    等方面
    0.90
    &-
    0.88
    %。
    0.88
    和
    0.86
    整数
    0.86
    ++;
    0.84
    %，
    0.82
    POSITIVE LOGITS
    rather
    2.15
     rather
    2.12
    Rather
    1.95
     Rather
    1.95
     plutôt
    1.44
    better
    1.43
     piuttosto
    1.35
     better
    1.33
    Instead
    1.28
     alternatively
    1.27
    Activations Density 0.075%

    No Known Activations