© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14582
    Prev
    Next
    INDEX
    Explanations

    number identifiers

    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
    olik
    2.53
    を実行
    2.36
    ynd
    2.32
    に限
    2.24
    場合は
    2.20
    acum
    2.19
    ง
    2.17
    iť
    2.17
    afe
    2.15
    ഷ്ട
    2.15
    POSITIVE LOGITS
    𝚖
    2.25
    ுகள்
    2.14
    棍
    1.97
    <bos>
    1.93
    𝚎
    1.88
    𝚢
    1.86
    𝚏
    1.86
     fre
    1.79
    軛
    1.75
     naught
    1.75
    Activations Density 0.004%

    No Known Activations