© 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. 131967
    Prev
    Next
    INDEX
    Explanations

    SoundCloud promo, stderr, stones, Slovakia

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

    AI requirements and safety

    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
    发的
    0.50
    \
    0.50
     št
    0.49
    发
    0.49
    )[
    0.48
    contributors
    0.47
    ié
    0.47
    l
    0.46
    全新
    0.46
     completa
    0.46
    POSITIVE LOGITS
     상당
    0.43
    टरी
    0.42
     상당히
    0.42
    стве
    0.42
    hadow
    0.41
     प्रतीत
    0.41
    Dart
    0.40
     cursory
    0.40
    ορ
    0.39
    भूत
    0.39
    Activations Density 0.001%

    No Known Activations