© 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. 13-GEMMASCOPE-2-RES-16K
    7. 7983
    Prev
    Next
    INDEX
    Explanations

    internal conflict

    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_13_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
     savait
    1.81
    ˖
    1.77
    হেতু
    1.69
     ér
    1.67
    abody
    1.63
    ძლი
    1.62
    abolic
    1.62
    setOnAction
    1.62
     결과
    1.60
    ாளர்கள்
    1.60
    POSITIVE LOGITS
    izde
    2.25
    spec
    2.19
    izers
    2.00
    ি
    2.00
    IZER
    1.93
    ised
    1.91
    inology
    1.90
    irati
    1.88
    izer
    1.85
    يل
    1.84
    Activations Density 0.122%

    No Known Activations