© 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. 10748
    Prev
    Next
    INDEX
    Explanations

    questions about purpose

    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
    िलं
    2.64
    […]
    2.52
    許
    2.49
    दयाल
    2.46
    ккей
    2.45
    ToBounds
    2.43
    𝚐
    2.41
    ogeneity
    2.41
     ocurre
    2.41
    heastern
    2.40
    POSITIVE LOGITS
    에
    2.80
    ا
    2.56
    sht
    2.56
    s
    2.53
     appraisals
    2.53
    펴
    2.49
    tap
    2.48
     눌
    2.47
    addons
    2.43
    iad
    2.41
    Activations Density 0.030%

    No Known Activations