© 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. 54025
    Prev
    Next
    INDEX
    Explanations

    Wikipedia article focus

    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
     CRIS
    0.45
     lista
    0.44
     PRINT
    0.44
     .
    0.43
     অ্যাপ
    0.43
     guérir
    0.43
     in
    0.42
     אם
    0.41
     Horticultural
    0.41
     início
    0.41
    POSITIVE LOGITS
    нул
    0.47
    SubSystem
    0.45
    ణాలు
    0.44
     ausencia
    0.44
    କୁ
    0.43
     Buccaneers
    0.43
    етесь
    0.43
    ନ
    0.43
    enziale
    0.42
    ћин
    0.42
    Activations Density 0.000%

    No Known Activations