© 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. 2362
    Prev
    Next
    INDEX
    Explanations

    Example Usage

    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
    ের
    3.11
    ים
    2.94
    ׁ
    2.75
    ৫
    2.52
    ה
    2.51
    ﻯ
    2.47
    的
    2.44
    ৮
    2.40
    Tocco
    2.30
    рис
    2.28
    POSITIVE LOGITS
    ‌هایی
    2.93
    ‌های
    2.69
    ariate
    2.53
    heastern
    2.52
    setScene
    2.49
    нном
    2.46
    umbing
    2.32
    opedic
    2.19
    ္ဂ
    2.18
    нным
    2.10
    Activations Density 0.062%

    No Known Activations