© 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. 184827
    Prev
    Next
    INDEX
    Explanations

    successfully converting

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

    assigning model roles or personas

    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
    لیل
    0.51
    зидента
    0.49
    rimination
    0.48
    لیم
    0.47
    φή
    0.47
    読んで
    0.47
    𝐞
    0.46
    侵害
    0.46
    Ⲕ
    0.45
    лім
    0.45
    POSITIVE LOGITS
     calming
    0.47
     Beacon
    0.43
     is
    0.42
     presto
    0.41
     حياة
    0.40
     routes
    0.40
     LIF
    0.39
     safety
    0.39
    jsko
    0.39
    ’
    0.39
    Activations Density 0.001%

    No Known Activations