© 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. 11010
    Prev
    Next
    INDEX
    Explanations

    cylindrical

    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
    𝘯
    2.63
     changeset
    2.20
    اء
    2.18
     ples
    2.15
     نامه
    2.12
    imeters
    2.10
    व्यों
    2.10
     Bürger
    2.08
    द
    2.07
     Qxc
    2.05
    POSITIVE LOGITS
    themealdb
    2.55
    簾
    2.51
    ্প্র
    2.47
    ாம
    2.46
    වා
    2.42
     напря
    2.40
    OrCreate
    2.36
    boxed
    2.35
     ditches
    2.34
    owią
    2.34
    Activations Density 0.028%

    No Known Activations