© 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. 100451
    Prev
    Next
    INDEX
    Explanations

    automobile parts and services

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

    competitive offering

    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
    hore
    0.48
     be
    0.48
    ПР
    0.46
    ।
    0.45
     PROJECT
    0.44
    м
    0.44
    ঞ্চলিক
    0.44
     خار
    0.44
    ío
    0.43
    y
    0.43
    POSITIVE LOGITS
     bây
    0.50
    羪
    0.49
     pann
    0.48
     pans
    0.48
     எந்த
    0.47
     Bây
    0.45
     现在
    0.45
     雨
    0.44
     bakt
    0.43
     Adequate
    0.42
    Activations Density 0.003%

    No Known Activations