© 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. 87310
    Prev
    Next
    INDEX
    Explanations

    questions followed by continuation

    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
    訁
    -1.71
    ༅
    -1.62
     conster
    -1.48
     odol
    -1.41
    觏
    -1.40
     enregistrer
    -1.40
     conçue
    -1.39
    碘
    -1.38
     dezelve
    -1.38
     данной
    -1.38
    POSITIVE LOGITS
    ?
    2.09
    0
    1.88
     also
    1.79
     or
    1.75
     sometimes
    1.68
     still
    1.62
     in
    1.54
    ....
    1.41
     always
    1.37
     has
    1.36
    Activations Density 0.020%

    No Known Activations