© 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. 66507
    Prev
    Next
    INDEX
    Explanations

    command and assist civil authorities

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

    water intrusion

    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
    ഫോ
    0.51
     שא
    0.48
    ա
    0.47
     vremena
    0.46
    HairColor
    0.46
     विवे
    0.44
    राम
    0.44
    樍
    0.44
    יל
    0.44
    Edad
    0.44
    POSITIVE LOGITS
     Guang
    0.49
     Schottky
    0.46
     characterised
    0.46
     telah
    0.46
     Contributing
    0.44
    studded
    0.43
    光
    0.43
     atta
    0.43
     synchrotron
    0.42
    普及
    0.42
    Activations Density 0.000%

    No Known Activations