Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 14686
    Prev
    Next
    INDEX
    Explanations

    discussing options

    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
    Trying
    0.49
    Cat
    0.48
    Tax
    0.48
     och
    0.47
    Tra
    0.47
    2
    0.47
    Architecture
    0.45
    )
    0.44
    Prediction
    0.43
    Frequency
    0.43
    POSITIVE LOGITS
    𝗴
    0.57
     кораб
    0.54
    yatiti
    0.54
     अत्याचार
    0.54
     atuação
    0.54
    ników
    0.50
     reused
    0.50
    ardı
    0.50
    avorable
    0.50
    čení
    0.50
    Activations Density 0.000%

    No Known Activations