© 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. 29108
    Prev
    Next
    INDEX
    Explanations

    API, paper trading

    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
    ა
    0.43
    т
    0.42
    lush
    0.38
    কে
    0.38
    ことに
    0.36
    тори
    0.35
    되
    0.35
    āla
    0.34
    q
    0.33
    Y
    0.32
    POSITIVE LOGITS
     wären
    0.42
     dwt
    0.40
     reactors
    0.39
     locomotive
    0.39
     signifikan
    0.38
     प्रौद्योगिकी
    0.37
     skiing
    0.37
     hvis
    0.36
     erros
    0.36
     speeding
    0.36
    Activations Density 0.000%

    No Known Activations