© 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. 262
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ing
    2.40
    培养
    2.29
     qualified
    2.29
    েও
    2.29
    вості
    2.27
     qualify
    2.26
    ു
    2.19
    o
    2.18
    rups
    2.17
    retto
    2.16
    POSITIVE LOGITS
    िक्रमा
    4.39
    此同时
    3.32
    ंपरा
    3.16
    slaught
    3.02
     towar
    2.89
    ෑම
    2.62
    cerning
    2.58
     وعلى
    2.58
    ("/",
    2.55
    ething
    2.54
    Activations Density 2.264%

    No Known Activations