© 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. 13948
    Prev
    Next
    INDEX
    Explanations

    claim that

    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
    ﾞ
    2.40
    ٹرول
    2.29
    ᴛ
    2.27
    ؤ
    2.26
    レーター
    2.20
    𝙩
    2.20
    दोस्तों
    2.19
    кли
    2.16
    anah
    2.12
    Добрый
    2.10
    POSITIVE LOGITS
    liness
    2.94
    sg
    2.59
    shmi
    2.54
    Ĭ
    2.34
    ‍ह
    2.33
    tilde
    2.29
    tree
    2.28
    swap
    2.26
    lard
    2.20
    ly
    2.20
    Activations Density 0.037%

    No Known Activations