© 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. 115007
    Prev
    Next
    INDEX
    Explanations

    traffic, submarines, ride

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

    practical considerations, scientific understanding, sensitive data

    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
    ①
    0.49
     thuốc
    0.48
    okok
    0.48
    бенок
    0.46
    Exclude
    0.46
     kt
    0.46
     kit
    0.45
     mivel
    0.45
    단
    0.43
    অনে
    0.43
    POSITIVE LOGITS
     heterogeneity
    0.47
     hierarchies
    0.46
    ைகளையும்
    0.45
     deplorable
    0.45
     evocative
    0.44
    歴史
    0.44
     challenging
    0.43
     thermodynamics
    0.43
     evolutionary
    0.42
    chromiumfx
    0.42
    Activations Density 0.003%

    No Known Activations