© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92349
    Prev
    Next
    INDEX
    Explanations

    algorithm definition or description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    encio
    0.52
     &/
    0.50
     مشرقی
    0.46
     apertura
    0.43
     fece
    0.42
    ल्दी
    0.42
     secession
    0.42
     Orlando
    0.41
     resistencia
    0.41
     fórmula
    0.41
    POSITIVE LOGITS
     dynamical
    0.55
    ∗
    0.54
     arXiv
    0.50
    arXiv
    0.50
     computational
    0.49
     parametrized
    0.49
    dynamical
    0.48
     ∗
    0.48
     bijection
    0.47
    Computational
    0.46
    Activations Density 0.005%

    No Known Activations