© 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. 22-GEMMASCOPE-2-RES-16K
    7. 539
    Prev
    Next
    INDEX
    Explanations

    philosophical debate and theory

    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_22_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
    瞒
    1.27
     Entfer
    1.20
     Equest
    1.17
    猙
    1.16
     parseFloat
    1.14
     récord
    1.12
    Nasdaq
    1.11
     فوتب
    1.08
    秒
    1.08
    密封
    1.07
    POSITIVE LOGITS
     theoretical
    1.90
     epistem
    1.89
     ethnographic
    1.87
     theor
    1.87
     methodological
    1.86
     theorists
    1.86
     scholarly
    1.79
     scholars
    1.79
    Theoretical
    1.77
     epistemology
    1.77
    Activations Density 2.312%

    No Known Activations