© 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. 66065
    Prev
    Next
    INDEX
    Explanations

    help with

    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
    :
    -2.58
     for
    -2.06
    ,
    -1.95
     from
    -1.81
    ).
    -1.72
     by
    -1.69
     other
    -1.66
     proportionate
    -1.64
     on
    -1.63
    género
    -1.61
    POSITIVE LOGITS
    这个问题
    1.93
    mäßigen
    1.73
    螄
    1.63
    ‟
    1.59
    вати
    1.59
     reali
    1.58
    ibilità
    1.55
    悭
    1.52
    ⢕
    1.52
     proble
    1.48
    Activations Density 0.015%

    No Known Activations