© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2230
    Prev
    Next
    INDEX
    Explanations

    sentence terminators

    np_acts-logits-general · gemini-2.5-flash-lite

    happy emojis and closing remarks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :'.
    0.36
    '".
    0.33
     endpoints
    0.31
    )".
    0.30
     ligands
    0.30
    )”.
    0.30
    ="'.$
    0.29
    вают
    0.29
     anatomic
    0.29
     datasets
    0.29
    POSITIVE LOGITS
     Also
    0.56
     Maybe
    0.56
     😊
    0.55
     Have
    0.55
    ↵↵↵↵
    0.55
     Sorry
    0.54
    ↵↵
    0.53
     Would
    0.53
     No
    0.52
     Note
    0.52
    Activations Density 0.536%

    No Known Activations