© 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. 17-GEMMASCOPE-2-RES-16K
    7. 22
    Prev
    Next
    INDEX
    Explanations

    saving code or files with example names

    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_17_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
    -
    0.82
    trans
    0.69
    บุ
    0.68
    ติ
    0.66
    artis
    0.65
     trans
    0.62
     staff
    0.61
    lok
    0.61
     crew
    0.61
    검
    0.60
    POSITIVE LOGITS
     चक्रवृद्धि
    1.61
     Calculating
    1.43
    Calculating
    1.40
     compounding
    1.39
     Calculator
    1.38
     Calculations
    1.37
    Exponent
    1.37
    Calculation
    1.34
     CAGR
    1.33
     CALCUL
    1.33
    Activations Density 0.042%

    No Known Activations