© 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. 851
    Prev
    Next
    INDEX
    Explanations

    names, places, and concepts

    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
     niekoľ
    1.22
     нескольких
    1.17
     представитель
    1.17
     рамках
    1.14
    ሮች
    1.13
    閩
    1.13
    шло
    1.13
    遠
    1.12
    ช่วง
    1.11
     прото
    1.11
    POSITIVE LOGITS
     should
    1.49
     cannot
    1.46
     says
    1.42
     must
    1.40
    '
    1.34
     could
    1.34
     lacks
    1.33
     wears
    1.32
     pretends
    1.32
     will
    1.31
    Activations Density 1.229%

    No Known Activations