© 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. 14336
    Prev
    Next
    INDEX
    Explanations

    wool and polar bear

    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
    는
    2.67
    yse
    2.66
    itth
    2.47
    चने
    2.43
     rangka
    2.42
    esam
    2.38
    동
    2.31
    ení
    2.30
    peuta
    2.29
    em
    2.25
    POSITIVE LOGITS
    s
    3.72
    ો
    3.48
    т
    3.43
    stion
    3.39
    मर्रा
    3.30
    רום
    3.25
    ು
    2.94
    ्स
    2.94
    िक्रमा
    2.93
    rrr
    2.90
    Activations Density 0.003%

    No Known Activations