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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13903
    Prev
    Next
    INDEX
    Explanations

    recursive function step

    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
    nh
    2.55
    ments
    2.51
     թվական
    2.47
    Á
    2.47
    MENTS
    2.44
    лох
    2.43
    σε
    2.43
    ZO
    2.36
    Ó
    2.35
    !("{
    2.33
    POSITIVE LOGITS
    esine
    3.20
    ة
    3.17
    een
    2.99
    esinde
    2.81
    ส์
    2.81
    esy
    2.80
    esinin
    2.73
    es
    2.70
    esini
    2.70
    eous
    2.56
    Activations Density 0.472%

    No Known Activations