© 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. 2157
    Prev
    Next
    INDEX
    Explanations

    efficiency

    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
    یت
    2.91
    يه
    2.74
    িতে
    2.72
    د
    2.67
    ion
    2.60
    ibility
    2.57
    ிக்
    2.57
    raster
    2.56
     दौड़
    2.55
    ья
    2.53
    POSITIVE LOGITS
    outube
    4.11
    yyyyyyyy
    4.10
    vonne
    3.72
    yyyy
    3.65
    untamiento
    3.65
    chelles
    3.64
    麼
    3.43
    ndrome
    3.42
    ển
    3.30
    LOADSTRING
    3.28
    Activations Density 1.567%

    No Known Activations