© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 1030
    Prev
    Next
    INDEX
    Explanations

    working together

    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_13_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
     incur
    1.66
    resp
    1.56
    瑁
    1.56
    खी
    1.50
    beard
    1.49
    ssymb
    1.49
     ghi
    1.48
     অনুষ্ঠ
    1.48
     зах
    1.47
    ophyllum
    1.44
    POSITIVE LOGITS
     tirelessly
    1.84
    zeuge
    1.72
    ఛ
    1.66
     harder
    1.63
    lungen
    1.63
    ेच्छा
    1.61
    溏
    1.60
    ŝ
    1.59
    ງານ
    1.57
    medskip
    1.57
    Activations Density 0.468%

    No Known Activations