© 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. 2931
    Prev
    Next
    INDEX
    Explanations

    debate and discussion

    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
    ه
    3.05
    ر
    2.88
    м
    2.88
    ി
    2.87
    вач
    2.78
    人不
    2.76
    a
    2.69
    u
    2.68
    iseur
    2.66
    يي
    2.65
    POSITIVE LOGITS
    ball
    2.27
    LOADSTRING
    2.26
    աք
    2.24
    theless
    2.16
    mleri
    2.12
    moor
    2.07
    Unnamed
    2.03
    FindAsync
    2.02
    ிருப்பது
    2.02
    trans
    2.01
    Activations Density 0.365%

    No Known Activations