© 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. 59326
    Prev
    Next
    INDEX
    Explanations

    free passed

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

    questions, numbers, neutral

    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
    ala
    0.52
    म
    0.52
    ల
    0.49
    Germany
    0.48
     և
    0.48
    ijen
    0.48
    Jo
    0.48
    ZW
    0.48
    SBOM
    0.47
    எ
    0.47
    POSITIVE LOGITS
     tinha
    0.55
     tinham
    0.55
    突
    0.51
    显示
    0.50
    屏
    0.50
    载
    0.49
     سیاه
    0.48
     நகா
    0.48
     bande
    0.46
    场景
    0.46
    Activations Density 0.000%

    No Known Activations