© 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. 119862
    Prev
    Next
    INDEX
    Explanations

    just that

    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
    ",
    -1.70
    </b>
    -1.45
    ,...
    -1.43
    imothy
    -1.41
    ',
    -1.41
     sério
    -1.39
    n
    -1.38
     engraçado
    -1.38
    le
    -1.36
    想了想
    -1.35
    POSITIVE LOGITS
     this
    1.88
    ябрь
    1.56
     that
    1.55
     every
    1.53
    嵙
    1.51
    moderne
    1.50
     katk
    1.49
    Nép
    1.48
     Sardegna
    1.46
    沒有
    1.41
    Activations Density 0.002%

    No Known Activations