© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64186
    Prev
    Next
    INDEX
    Explanations

    templates and generic types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <>
    -0.97
     <>
    -0.90
     its
    -0.75
    开发
    -0.75
     \%
    -0.75
     STILL
    -0.73
     CSS
    -0.71
    ഠ
    -0.71
     still
    -0.71
    　・
    -0.71
    POSITIVE LOGITS
    <
    1.66
     <
    1.27
    '><
    0.98
    ]<
    0.93
     توانید
    0.82
    ϫ
    0.79
     cérami
    0.78
    Pru
    0.78
     dessins
    0.77
    ﻚ
    0.77
    Activations Density 0.086%

    No Known Activations