© 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. 10935
    Prev
    Next
    INDEX
    Explanations

    OPT, CPT, keyword, abbreviations

    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
    י
    2.76
    Maritime
    2.53
    eed
    2.49
    hipping
    2.37
     Maritime
    2.35
    Hara
    2.35
    DAS
    2.33
    EEEE
    2.33
    ᆻ
    2.30
    equ
    2.30
    POSITIVE LOGITS
    aneously
    2.66
    BackPressed
    2.63
    ्य
    2.59
    容
    2.59
    пло
    2.43
    ैक
    2.39
    ful
    2.35
    ੀਆਂ
    2.35
    পক্ষে
    2.31
     izinsuku
    2.29
    Activations Density 0.006%

    No Known Activations