© 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. 39951
    Prev
    Next
    INDEX
    Explanations

    in service address

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

    llama 3 or symmetry

    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
    鹖
    0.50
     ἐν
    0.49
    ोली
    0.48
     aline
    0.47
    يد
    0.47
    ܕ
    0.46
    ה
    0.46
     miembro
    0.46
    ಿಯೇ
    0.46
     revelation
    0.45
    POSITIVE LOGITS
    TON
    0.50
    君
    0.49
    故
    0.47
    ERI
    0.43
    概
    0.43
    ION
    0.42
    善
    0.42
    hiro
    0.42
    吞
    0.42
    ROS
    0.42
    Activations Density 0.000%

    No Known Activations