© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 157938
    Prev
    Next
    INDEX
    Explanations

    risk of fire

    np_acts-logits-general · gemini-2.5-flash-lite

    business, health outcomes, and time limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     ၀
    0.48
    HEADERS
    0.46
     chil
    0.46
    PathTemplate
    0.46
     aritm
    0.45
     رسمي
    0.45
    সপ
    0.45
     honti
    0.45
    ropolit
    0.44
    }+(\
    0.44
    POSITIVE LOGITS
    ี่
    0.57
    ха
    0.48
    <0x94>
    0.46
    ibranch
    0.46
    <0x91>
    0.42
     sounding
    0.42
    วัติ
    0.42
    зей
    0.41
    ซึ่ง
    0.41
     squiggle
    0.41
    Activations Density 0.000%

    No Known Activations