© 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. 190873
    Prev
    Next
    INDEX
    Explanations

    services, reception, universal

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

    technical terms and concepts

    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
    ों
    0.53
     Podcast
    0.51
     Mone
    0.50
     Benefits
    0.50
    ের
    0.49
    s
    0.48
    컵
    0.48
     an
    0.47
     Translation
    0.47
    چھے
    0.46
    POSITIVE LOGITS
    ngen
    0.48
    niger
    0.48
     murderous
    0.47
     bituminous
    0.47
     brook
    0.46
    westen
    0.46
     نو
    0.46
     epithelial
    0.44
     وسی
    0.44
    v
    0.44
    Activations Density 0.000%

    No Known Activations