© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12072
    Prev
    Next
    INDEX
    Explanations

    API endpoint paths

    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
    dey
    2.39
    на
    2.39
    ي
    2.37
    нару
    2.33
    y
    2.32
    setCurrent
    2.29
    𝗇
    2.29
     predic
    2.25
    𝗌
    2.22
    ⃞
    2.20
    POSITIVE LOGITS
     חיצוני
    2.01
    𝐦
    2.01
    "?
    1.99
    "，
    1.98
    iframe
    1.92
    ACITY
    1.92
    "!
    1.91
     grail
    1.90
    "。
    1.89
    brella
    1.86
    Activations Density 0.001%

    No Known Activations