© 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. 51688
    Prev
    Next
    INDEX
    Explanations

    stages or initial conditions

    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
    স্পতিবার
    0.47
     surged
    0.45
    <unused2153>
    0.44
    場合は
    0.43
     absenteeism
    0.43
    განი
    0.43
     yarg
    0.42
    ೮
    0.41
    cmt
    0.41
     मोस्ट
    0.41
    POSITIVE LOGITS
     бага
    0.50
    ตี
    0.45
    ท่า
    0.44
    ๆ
    0.43
    冝
    0.43
    ที่
    0.43
    에서의
    0.43
    าะ
    0.42
    砣
    0.42
     ማድረግ
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.