© 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. 10-GEMMASCOPE-RES-131K
    7. 61434
    Prev
    Next
    INDEX
    Explanations

    special [noun]

    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_10/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
    er
    -2.56
    猡
    -2.53
    ೢ
    -2.36
    
    -2.36
    鸶
    -2.31
    硨
    -2.30
    ه
    -2.28
    ༷
    -2.25
    
    -2.23
    鹪
    -2.22
    POSITIVE LOGITS
    Obviously
    3.13
    Probably
    3.02
    ).
    2.95
    Usually
    2.94
    Interestingly
    2.92
    Although
    2.92
    Initially
    2.91
    Ironically
    2.91
    There
    2.84
    Essentially
    2.83
    Activations Density 0.010%

    No Known Activations