© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 125809
    Prev
    Next
    INDEX
    Explanations

    distances, speed, extracted, made

    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
    años
    0.53
    ıl
    0.50
    untuk
    0.48
    re
    0.46
    uetooth
    0.45
    ｺ
    0.45
    nje
    0.44
    entuk
    0.44
     रूप
    0.44
    awsze
    0.44
    POSITIVE LOGITS
    出來
    0.45
     quotients
    0.42
    出去
    0.41
     raff
    0.40
     超
    0.40
     যাত্রা
    0.39
     largos
    0.39
    崑
    0.39
    廣場
    0.39
     groß
    0.38
    Activations Density 0.010%

    No Known Activations