© 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. 7847
    Prev
    Next
    INDEX
    Explanations

    examples in lists

    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
    :
    1.25
    either
    1.23
    :*
    1.14
    ：
    1.10
    েরই
    1.01
    :\
    1.01
    :${
    0.99
    rodní
    0.98
    Either
    0.98
    :‏
    0.97
    POSITIVE LOGITS
     etc
    5.35
    etc
    4.73
    等
    4.48
     Etc
    4.40
    等等
    4.38
     usw
    4.34
    など
    4.33
     등
    4.28
     등이
    4.19
     등의
    4.12
    Activations Density 0.308%

    No Known Activations