© 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. 124956
    Prev
    Next
    INDEX
    Explanations

    the figure is

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

    teaching and learning from 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
    ರ್ಶ
    0.53
     síntomas
    0.53
    뇰
    0.49
    商城
    0.48
    سن
    0.48
     обеща
    0.48
    狠狠
    0.48
    旅遊
    0.46
    唵
    0.46
    न्या
    0.45
    POSITIVE LOGITS
     Prerequisites
    0.53
     Wakefield
    0.53
     Connections
    0.51
     prisms
    0.49
     Graphite
    0.48
     Acts
    0.48
     Prisma
    0.48
     contaminants
    0.47
     Adults
    0.47
     connections
    0.47
    Activations Density 0.002%

    No Known Activations