© 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. 10956
    Prev
    Next
    INDEX
    Explanations

    certain point in time

    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
    skirts
    2.75
    −</
    2.64
    ⠉
    2.61
    𝕊
    2.55
    𝕖
    2.41
    reliable
    2.39
    sklär
    2.38
    SEQ
    2.35
    𝕒
    2.34
    REGEX
    2.34
    POSITIVE LOGITS
    ا
    3.13
    er
    2.86
    ek
    2.68
    ের
    2.60
    ي
    2.54
    europa
    2.40
    क्स्ट
    2.35
    alogy
    2.34
    اك
    2.33
    ıya
    2.30
    Activations Density 0.038%

    No Known Activations