© 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. 178996
    Prev
    Next
    INDEX
    Explanations

    pupil receives

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

    tokenization variations, language

    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
    西
    0.44
    毫
    0.44
     intermitt
    0.44
     stá
    0.43
     در
    0.42
     hand
    0.42
    });
    0.41
    莫名
    0.41
     droid
    0.40
     échange
    0.40
    POSITIVE LOGITS
     लिव
    0.61
    tailwindcss
    0.55
    rekt
    0.54
    lessis
    0.53
     Yucatán
    0.53
    ey
    0.53
     巻
    0.52
    amise
    0.52
     優
    0.51
    ac
    0.50
    Activations Density 0.001%

    No Known Activations