© 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. 102575
    Prev
    Next
    INDEX
    Explanations

    dream

    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
    lecht
    -1.63
     esigen
    -1.60
    ござい
    -1.54
    ');
    -1.53
    出来る
    -1.52
    ﾍ
    -1.52
     whom
    -1.50
    2
    -1.48
     \
    -1.47
    くださいね
    -1.46
    POSITIVE LOGITS
    .
    1.53
     baut
    1.42
     japones
    1.42
     bygget
    1.41
     dziś
    1.40
    يه
    1.38
     rafra
    1.35
    蟊
    1.34
     لأن
    1.34
    HOSTS
    1.34
    Activations Density 0.014%

    No Known Activations