© 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. 2059
    Prev
    Next
    INDEX
    Explanations

    supports and capabilities

    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
    -/
    1.66
     oder
    1.45
    "/"
    1.38
     ou
    1.35
    ons
    1.22
     or
    1.21
     eller
    1.21
     maupun
    1.19
     ataupun
    1.19
    /
    1.16
    POSITIVE LOGITS
     корпус
    1.69
    وضح
    1.68
     Ху
    1.66
     江
    1.66
     इसके
    1.66
    ﻜ
    1.65
    ﻪ
    1.65
    尼
    1.64
    ﺔ
    1.63
     嗯
    1.63
    Activations Density 0.237%

    No Known Activations