© 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. 11444
    Prev
    Next
    INDEX
    Explanations

    intent or purpose inquiries

    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
    and
    1.69
    และ
    1.52
    または
    1.40
    And
    1.39
    ande
    1.32
    和
    1.31
    If
    1.30
    ands
    1.30
    You
    1.30
    ibus
    1.29
    POSITIVE LOGITS
     "`
    1.46
     Sở
    1.36
     类型
    1.36
     其
    1.35
     די
    1.29
     ק
    1.29
     られ
    1.25
    捌章
    1.25
     ל
    1.24
     предмет
    1.24
    Activations Density 0.047%

    No Known Activations