© 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. 27888
    Prev
    Next
    INDEX
    Explanations

    SMS capability

    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
    stilling
    0.44
    본
    0.43
    чила
    0.42
     삼
    0.41
     प्लांट
    0.41
    노
    0.41
     ഭ
    0.41
     образование
    0.41
    苷
    0.41
     교육
    0.41
    POSITIVE LOGITS
    پيديا
    0.45
     manoeuv
    0.44
     entice
    0.43
     interle
    0.43
    Inet
    0.41
    ظيم
    0.41
     gestão
    0.40
     gestione
    0.39
     tmux
    0.39
    وى
    0.39
    Activations Density 0.003%

    No Known Activations