© 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. 251919
    Prev
    Next
    INDEX
    Explanations

    business services and logistics

    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
    qPCR
    0.57
    ת
    0.57
    MDEwOlJlcG
    0.55
    മാനം
    0.54
     发表
    0.53
    阝
    0.51
     イエロー
    0.49
     UIS
    0.48
     __('
    0.48
    防水
    0.48
    POSITIVE LOGITS
    I
    0.42
    -
    0.42
     plank
    0.41
     цін
    0.40
    Ins
    0.39
    ție
    0.39
    Thing
    0.39
     Tahun
    0.39
    ُ
    0.38
    *
    0.38
    Activations Density 0.000%

    No Known Activations