© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84738
    Prev
    Next
    INDEX
    Explanations

    words starting with Cel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    datetime
    -0.84
     supers
    -0.73
     NGOs
    -0.72
     Ranked
    -0.70
    styp
    -0.69
    requirement
    -0.68
    amatkan
    -0.68
     bawa
    -0.67
    _______________
    -0.67
    subs
    -0.67
    POSITIVE LOGITS
    clearfix
    0.71
     clearfix
    0.71
     Fellow
    0.71
    َي
    0.70
    ITAL
    0.70
     tấn
    0.70
    alyptus
    0.69
    ptions
    0.69
    đen
    0.69
     ऐसा
    0.68
    Activations Density 0.029%

    No Known Activations