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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10628
    Prev
    Next
    INDEX
    Explanations

    rotating, start, scientist, primary, reminders

    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
     bilo
    0.84
     biến
    0.81
     Mong
    0.81
     দ
    0.79
     ㄴ
    0.79
     বাধা
    0.77
     AnyObject
    0.76
     berarti
    0.75
     Rxf
    0.73
     Manip
    0.73
    POSITIVE LOGITS
    arus
    1.16
    ooter
    1.15
    ეგისტრ
    1.09
    decimal
    1.08
    <unused1013>
    1.08
    excess
    1.07
    しばらく
    1.07
    counts
    1.07
    ან
    1.06
    isalpha
    1.06
    Activations Density 0.000%

    No Known Activations