© 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. 525
    Prev
    Next
    INDEX
    Explanations

    code identifiers and syntax

    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
     normative
    1.79
     interrelated
    1.77
     digamos
    1.70
     macroeconomic
    1.68
    럇
    1.66
    핞
    1.64
     diffe
    1.64
     attribution
    1.64
     maximization
    1.60
    ᆞ
    1.59
    POSITIVE LOGITS
    ’
    1.73
    '
    1.43
    awang
    1.36
    ↵↵↵
    1.35
    ará
    1.33
    3
    1.31
    ↵↵↵↵↵
    1.26
    2
    1.26
    arul
    1.24
    1
    1.24
    Activations Density 0.067%

    No Known Activations