© 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. 10023
    Prev
    Next
    INDEX
    Explanations

    reading file paths

    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
     hexagonal
    0.84
    readable
    0.79
    Arms
    0.77
    家に
    0.77
     bits
    0.76
    <start_of_image>
    0.75
    庚
    0.75
    튼
    0.75
    घरों
    0.73
     doubtless
    0.73
    POSITIVE LOGITS
    úč
    0.93
    ocally
    0.92
     HttpStatus
    0.88
     средства
    0.88
    颊
    0.88
     ін
    0.87
     AUX
    0.87
    ี่ป
    0.86
    čené
    0.85
     BadRequest
    0.84
    Activations Density 0.002%

    No Known Activations