© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 84132
    Prev
    Next
    INDEX
    Explanations

    flag information

    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
     processi
    0.44
     във
    0.44
     процессы
    0.42
    狀
    0.42
    जलवायु
    0.42
     растение
    0.41
     enzymatic
    0.40
     transferencia
    0.40
    стре
    0.39
    ,
    0.39
    POSITIVE LOGITS
    वीन
    0.44
    istä
    0.42
    هان
    0.41
    moid
    0.40
     worthless
    0.39
     समझौता
    0.39
     eqs
    0.39
     شود
    0.39
     مال
    0.39
     막
    0.38
    Activations Density 0.014%

    No Known Activations