© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7110
    Prev
    Next
    INDEX
    Explanations

    article titles

    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_22_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
     ครั้ง
    0.92
     mécanique
    0.90
     തവണ
    0.89
     इस्तीफा
    0.85
     کرده
    0.85
     pact
    0.84
    ރ
    0.84
    எம்
    0.84
    锢
    0.83
     Küchen
    0.80
    POSITIVE LOGITS
     profit
    1.97
     Profit
    1.81
    profit
    1.81
     profits
    1.77
    Profit
    1.65
     Profits
    1.58
    profits
    1.49
     PROFITS
    1.36
    盈利
    1.31
    利润
    1.31
    Activations Density 0.119%

    No Known Activations