© 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. 7-GEMMASCOPE-2-RES-16K
    7. 60
    Prev
    Next
    INDEX
    Explanations

    code keywords and libraries

    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
     형성
    1.85
    WWE
    1.83
     macho
    1.80
    flight
    1.75
     crazy
    1.75
    𝐚
    1.73
    Crazy
    1.69
    CCCCCC
    1.66
    şey
    1.66
    柱
    1.66
    POSITIVE LOGITS
    gica
    1.66
    endpoint
    1.63
    ldef
    1.60
     ఫలి
    1.55
     जाइए
    1.54
    uchten
    1.52
     Exceptions
    1.50
    leni
    1.49
    ෙන්
    1.47
     Prospective
    1.47
    Activations Density 0.060%

    No Known Activations