© 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. 234069
    Prev
    Next
    INDEX
    Explanations

    specific groups or entities

    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
     exigences
    0.46
     requisito
    0.46
    まま
    0.46
    多家
    0.46
     سلي
    0.44
     +=
    0.44
     вимо
    0.43
     liné
    0.42
    ض
    0.41
    قار
    0.41
    POSITIVE LOGITS
    downs
    0.54
    räger
    0.52
    detection
    0.51
    diamond
    0.50
    colorful
    0.50
    humans
    0.50
    rawy
    0.49
    teman
    0.49
    students
    0.48
    elite
    0.48
    Activations Density 0.001%

    No Known Activations