© 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. 9996
    Prev
    Next
    INDEX
    Explanations

    needs to understand

    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
    joe
    0.98
    鹕
    0.94
    ಒ
    0.92
     உண்மைய
    0.91
    ONLY
    0.91
    햐
    0.89
    무리
    0.89
    ון
    0.89
    믈
    0.89
    öld
    0.88
    POSITIVE LOGITS
     bedtime
    0.94
     ле
    0.93
     момента
    0.87
     Elles
    0.86
     restit
    0.85
     they
    0.85
     own
    0.84
     drawn
    0.84
     elles
    0.84
     settembre
    0.83
    Activations Density 0.000%

    No Known Activations