© 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. 759
    Prev
    Next
    INDEX
    Explanations

    It focuses, but uses

    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
    ুজ
    1.63
    Integer
    1.55
     মুহুর
    1.54
    সময়
    1.51
    HttpMethod
    1.50
     Eindruck
    1.44
    iam
    1.44
    ---------------+
    1.44
    Hashing
    1.42
    FirstName
    1.42
    POSITIVE LOGITS
     foaming
    1.96
     reeling
    1.83
    GORITH
    1.77
    apek
    1.74
     opener
    1.71
    bė
    1.70
    nul
    1.68
    owymi
    1.67
     susp
    1.67
    스테
    1.66
    Activations Density 0.380%

    No Known Activations