© 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. 94191
    Prev
    Next
    INDEX
    Explanations

    suspect something unusual

    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
    z
    0.51
    aya
    0.48
    u
    0.45
    ATION
    0.44
    omeres
    0.44
    𝗴
    0.43
    ad
    0.43
    ambarkan
    0.43
    &\
    0.42
    ari
    0.42
    POSITIVE LOGITS
     esfuerzos
    0.60
     deprec
    0.59
     ولكن
    0.57
     reluct
    0.54
     الت
    0.54
     publicaciones
    0.53
     تجاه
    0.53
     esforços
    0.53
     تغيير
    0.52
     nonchal
    0.52
    Activations Density 0.001%

    No Known Activations