© 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. 14144
    Prev
    Next
    INDEX
    Explanations

    efficiency and productivity

    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
    reg
    2.28
     s
    2.06
    has
    2.05
     Un
    1.88
    red
    1.83
    후
    1.81
    ങ്ങാ
    1.80
    language
    1.76
     ab
    1.73
     na
    1.72
    POSITIVE LOGITS
    くちゃ
    3.50
    лкой
    3.31
    <unused969>
    3.31
     setTodos
    3.23
    etição
    3.22
    علم
    3.21
     separación
    3.20
    CycleOffset
    3.18
    ﭔ
    3.11
     divisão
    3.11
    Activations Density 0.006%

    No Known Activations