© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-65K
    4. 1366
    Prev
    Next
    INDEX
    Explanations

    0 times, calculations

    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_65k_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
     Handle
    1.84
    Handle
    1.69
    Scissors
    1.66
     כן
    1.64
     효과
    1.61
    ﻦ
    1.61
     כאשר
    1.58
     Horus
    1.57
     HANDLE
    1.56
     Invoke
    1.55
    POSITIVE LOGITS
    trp
    1.36
     anden
    1.34
    chst
    1.31
     transnational
    1.28
    كتور
    1.27
    roits
    1.26
    서는
    1.26
    暫
    1.26
    セン
    1.25
    го
    1.25
    Activations Density 0.000%

    No Known Activations