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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 856
    Prev
    Next
    INDEX
    Explanations

    code main function starter

    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_7_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
     pre
    1.43
    pre
    1.16
     trouble
    1.14
     Ford
    1.11
     pause
    1.10
    ↵↵
    1.09
     conclusion
    1.09
     Pre
    1.09
    ↵
    1.05
    <strong>
    1.05
    POSITIVE LOGITS
     антен
    1.78
    伊
    1.72
     vijj
    1.71
     અને
    1.70
     لل
    1.67
    नव
    1.67
    <unused851>
    1.66
     στις
    1.65
     फीफा
    1.65
    शाही
    1.63
    Activations Density 0.291%

    No Known Activations