© 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. 199573
    Prev
    Next
    INDEX
    Explanations

    explaining concepts and strategies

    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
     Bus
    0.51
    の
    0.47
    メタ
    0.45
    ’
    0.45
    의
    0.45
     Mó
    0.45
     Soda
    0.43
     publie
    0.42
    '
    0.42
     Cup
    0.42
    POSITIVE LOGITS
     设计
    0.54
     شرطونو
    0.51
     问题
    0.48
     princípios
    0.48
     giocando
    0.48
    ifting
    0.47
    ሳሪያ
    0.46
     гуляць
    0.45
    VarArgs
    0.45
    mean
    0.45
    Activations Density 0.001%

    No Known Activations