© 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. 221509
    Prev
    Next
    INDEX
    Explanations

    second Microsoft

    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
     wre
    0.46
     fondness
    0.46
    <0xA8>
    0.44
     luat
    0.44
    ˧
    0.44
     MAGAZINE
    0.43
    ੭
    0.43
    쨋
    0.43
    ﺲ
    0.43
    不死
    0.42
    POSITIVE LOGITS
     همان
    0.44
    iam
    0.44
    át
    0.43
     pairs
    0.42
     overlaps
    0.42
     رکن
    0.42
     déten
    0.41
    ien
    0.41
    atis
    0.40
     Tree
    0.40
    Activations Density 0.000%

    No Known Activations