© 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. 202409
    Prev
    Next
    INDEX
    Explanations

    technical terms and programming syntax

    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
     Ευ
    0.54
     Акы
    0.54
     Signific
    0.52
    ColorBit
    0.52
     作り
    0.52
    깆
    0.51
     прода
    0.51
     канале
    0.51
    saya
    0.51
    डली
    0.51
    POSITIVE LOGITS
    consumed
    0.42
    lysis
    0.42
     virulent
    0.41
     hom
    0.41
    Dw
    0.41
     collapsed
    0.41
     defeating
    0.41
     collapsing
    0.41
     paralle
    0.40
    閉
    0.40
    Activations Density 0.002%

    No Known Activations