© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11759
    Prev
    Next
    INDEX
    Explanations

    plotting labels

    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
    輳
    1.71
    Weyl
    1.65
    ಿನಲ್ಲಿ
    1.63
     hounds
    1.61
    Следу
    1.61
    setPreferredSize
    1.57
    ின்
    1.54
    InChildren
    1.54
    周囲
    1.53
    風格
    1.52
    POSITIVE LOGITS
    िके
    1.64
    SubType
    1.60
     Jov
    1.56
     Intellectual
    1.55
    šia
    1.50
    𝐤
    1.44
    रावर
    1.43
    frigerator
    1.43
     Simulated
    1.43
    ڳ
    1.42
    Activations Density 0.000%

    No Known Activations