© 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. 102155
    Prev
    Next
    INDEX
    Explanations

    ocean blue water products

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

    file extensions and technical terms

    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
    tax
    0.50
    blogger
    0.48
    fue
    0.46
    ंदा
    0.44
    ╰
    0.44
     resulted
    0.44
    generation
    0.44
    gano
    0.43
    theo
    0.41
    減
    0.41
    POSITIVE LOGITS
    澫
    0.51
     algebras
    0.49
     liitty
    0.49
    Suffix
    0.48
     период
    0.47
     путь
    0.47
    SV
    0.47
    Prefix
    0.46
    SVG
    0.46
     etapas
    0.46
    Activations Density 0.001%

    No Known Activations