© 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. 40-GEMMASCOPE-2-RES-262K
    7. 134333
    Prev
    Next
    INDEX
    Explanations

    creating or composing things

    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_40_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
     заболевания
    0.40
     empir
    0.39
    ulaires
    0.38
    わたし
    0.38
    マリン
    0.38
    誢
    0.38
    owań
    0.37
    𒋢
    0.37
    вань
    0.37
     logiciels
    0.37
    POSITIVE LOGITS
     practically
    0.40
     Q
    0.39
     गिन
    0.39
    问
    0.39
    ON
    0.38
     du
    0.38
    ay
    0.38
    có
    0.38
     single
    0.38
    aryng
    0.38
    Activations Density 0.001%

    No Known Activations