© 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. 130455
    Prev
    Next
    INDEX
    Explanations

    keywords in code declarations

    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
    辔
    -1.89
    kurtka
    -1.82
     expliquer
    -1.81
    sukienka
    -1.79
     appeler
    -1.76
    spodnie
    -1.70
     wortel
    -1.63
    +</
    -1.62
     négo
    -1.61
    昞
    -1.60
    POSITIVE LOGITS
    )
    2.16
     from
    2.00
    ir
    1.86
    [
    1.77
     of
    1.77
     are
    1.77
    .,
    1.76
    ll
    1.76
    ]
    1.70
    1
    1.66
    Activations Density 0.018%

    No Known Activations