© 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. 12520
    Prev
    Next
    INDEX
    Explanations

    Austin Butler, Austin TX

    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
    sila
    2.85
    ات
    2.76
    tol
    2.76
    tum
    2.66
    tres
    2.66
    ti
    2.65
    tin
    2.65
    __(/*!
    2.64
    ingar
    2.63
    ING
    2.63
    POSITIVE LOGITS
    ————————
    2.96
    ע
    2.85
    FolderPath
    2.63
    centralwidget
    2.61
    ————————————————
    2.55
    ˣ
    2.51
    প্তাহ
    2.47
    Հ
    2.42
    libs
    2.41
    Device
    2.39
    Activations Density 0.004%

    No Known Activations