© 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. 241218
    Prev
    Next
    INDEX
    Explanations

    business practices or expansion

    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
     HELP
    0.50
     ∑
    0.49
     smeared
    0.48
     muffled
    0.48
     noun
    0.47
     थक
    0.47
     αποτέ
    0.47
     magnified
    0.46
     muñ
    0.46
     गु
    0.46
    POSITIVE LOGITS
    මත්
    0.50
    М
    0.47
    meyen
    0.46
     عبدالله
    0.45
     altında
    0.45
    arda
    0.44
    湋
    0.43
    Increased
    0.42
    경기도
    0.42
    เชสเตอร์
    0.42
    Activations Density 0.001%

    No Known Activations