© 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. 137971
    Prev
    Next
    INDEX
    Explanations

    characters,ortools

    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
     स्वा
    0.47
     ER
    0.46
     huge
    0.45
     Simple
    0.44
     i
    0.44
    0.44
     I
    0.44
     Voluntary
    0.42
     Huge
    0.42
     AR
    0.42
    POSITIVE LOGITS
    ോഗ്യ
    0.47
     песен
    0.46
     avem
    0.46
    荕
    0.46
     avantaj
    0.45
    㑨
    0.44
    рабаты
    0.44
     efficacement
    0.44
     idempot
    0.44
    ан
    0.43
    Activations Density 0.006%

    No Known Activations