© 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. 126716
    Prev
    Next
    INDEX
    Explanations

    strengths and weaknesses

    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
     trajets
    0.48
    Concini
    0.48
    꽉
    0.45
    ক্ক
    0.45
     danse
    0.43
    itzar
    0.43
     lyr
    0.43
    लंका
    0.42
    Masukkan
    0.42
    Ᏹ
    0.42
    POSITIVE LOGITS
    ↵
    0.48
     (
    0.46
     Redwood
    0.44
     Sputnik
    0.44
     October
    0.43
     Hart
    0.43
    certain
    0.43
     highlights
    0.42
     свидетель
    0.42
     Highlights
    0.42
    Activations Density 0.003%

    No Known Activations