© 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. 21746
    Prev
    Next
    INDEX
    Explanations

    tokens followed by specific continuations

    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
     DIFFERENT
    -2.13
     genellikle
    -2.02
    臜
    -1.90
     ‘
    -1.84
     cuenca
    -1.82
    颯
    -1.81
    
    -1.74
    ffen
    -1.73
     JD
    -1.72
    paisaje
    -1.68
    POSITIVE LOGITS
    The
    2.23
    This
    2.22
    這樣
    2.20
    érape
    2.09
    These
    1.98
    What
    1.97
     you
    1.96
    Very
    1.95
    Most
    1.91
     setelah
    1.91
    Activations Density 0.001%

    No Known Activations