© 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. 10329
    Prev
    Next
    INDEX
    Explanations

    provider for

    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
     између
    0.94
     маса
    0.91
     excepciones
    0.91
    濱
    0.90
     espero
    0.89
    гина
    0.87
    焚
    0.86
    엌
    0.86
    маш
    0.86
    APPENDIX
    0.85
    POSITIVE LOGITS
     technology
    1.34
     measure
    1.11
     contemporary
    1.11
     tehn
    1.10
     technolog
    1.08
     tecnologia
    1.07
     perceived
    1.06
     technologically
    1.06
    technology
    1.05
    ately
    1.03
    Activations Density 0.004%

    No Known Activations