© 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. 190799
    Prev
    Next
    INDEX
    Explanations

    make any, an exemption, completed, home, architecture

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

    project activities

    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
     betreff
    0.60
    ll
    0.54
    ７
    0.50
    7
    0.49
    minor
    0.49
    mount
    0.48
    0.48
    million
    0.48
    seven
    0.47
     hebdom
    0.47
    POSITIVE LOGITS
    그리고
    0.56
    워크
    0.51
    и
    0.50
     instantiation
    0.49
     TASK
    0.48
    듯
    0.48
     escolher
    0.47
    그러
    0.47
    َهُ
    0.47
     ORGANIZATION
    0.46
    Activations Density 0.000%

    No Known Activations