© 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. 13-GEMMASCOPE-2-RES-16K
    7. 8991
    Prev
    Next
    INDEX
    Explanations

    list items, tables, and analytics

    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
    kania
    1.85
    ูน
    1.85
     μέσω
    1.81
    捅
    1.78
    ゚
    1.76
    ச்சியை
    1.73
    ძლიათ
    1.72
     કૃ
    1.72
    வார
    1.71
    ச்ச
    1.71
    POSITIVE LOGITS
    assign
    1.63
    nte
    1.58
     geomet
    1.48
    vier
    1.41
    chst
    1.40
    vous
    1.40
     injectors
    1.38
     elves
    1.37
    freetype
    1.36
    꼴
    1.34
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.