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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10108
    Prev
    Next
    INDEX
    Explanations

    incentives encourage

    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
    創意
    0.98
     ><
    0.92
     Shay
    0.91
    他們的
    0.90
    他们的
    0.90
     BAK
    0.88
     their
    0.88
    菊花
    0.87
    藝術
    0.85
     ಥ
    0.85
    POSITIVE LOGITS
    ्याने
    0.97
     erfüllen
    0.92
    ேத்க
    0.89
    wh
    0.89
    ığımızda
    0.87
    द्वानी
    0.87
    filtr
    0.86
     będzie
    0.85
    adale
    0.85
    ïde
    0.85
    Activations Density 0.000%

    No Known Activations