© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15042
    Prev
    Next
    INDEX
    Explanations

    mathematical section headers

    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
    脔
    -1.96
    ของ
    -1.77
    .
    -1.75
    voer
    -1.63
    عرِّف
    -1.61
    }$.
    -1.59
    .\"
    -1.59
    。
    -1.59
     dades
    -1.54
     direita
    -1.53
    POSITIVE LOGITS
    .
    2.47
    :
    2.41
    ,
    2.13
     it
    1.81
     Compared
    1.62
    0
    1.58
    Usually
    1.55
    Typically
    1.52
    Generally
    1.52
    Though
    1.50
    Activations Density 0.002%

    No Known Activations