© 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. 3743
    Prev
    Next
    INDEX
    Explanations

    a lot

    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
    |}
    2.92
    𝓲
    2.91
    
    2.82
    iciency
    2.69
    %"},
    2.65
    ────────
    2.64
    casian
    2.62
    ⁢</
    2.58
    Č
    2.57
     typesetting
    2.56
    POSITIVE LOGITS
    ்
    2.78
    ful
    2.50
     asyncio
    2.44
    orn
    2.42
    aio
    2.41
    ل
    2.38
    rella
    2.31
    ung
    2.27
    ്രി
    2.26
    רות
    2.23
    Activations Density 0.074%

    No Known Activations