© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1666
    Prev
    Next
    INDEX
    Explanations

    competitive landscape and compile

    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
    ゙
    2.19
    h
    2.15
    коном
    2.14
    ப
    2.13
     podr
    2.05
    ہ
    2.04
    asgi
    1.95
     harn
    1.94
    f
    1.93
    ulton
    1.93
    POSITIVE LOGITS
    ﮄ
    3.27
    Drawing
    2.94
    ﻞ
    2.93
    Study
    2.89
    ﹟
    2.84
    eteries
    2.81
    &$\
    2.79
     Drawing
    2.78
    Against
    2.75
    ερμαν
    2.73
    Activations Density 0.245%

    No Known Activations