© 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. 250
    Prev
    Next
    INDEX
    Explanations

    question / answer structure

    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
     xuống
    1.73
    ERTS
    1.70
     dàng
    1.64
    ို
    1.54
    няют
    1.53
    чём
    1.47
    漿
    1.44
    Бы
    1.43
     套
    1.43
    OURCE
    1.42
    POSITIVE LOGITS
    GridLayout
    2.04
    rank
    2.02
     minSdkVersion
    1.95
     Stratford
    1.93
     Warwick
    1.93
    artiste
    1.90
     মনো
    1.86
    va
    1.85
     alanı
    1.83
    itiv
    1.82
    Activations Density 0.000%

    No Known Activations