© 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. 59210
    Prev
    Next
    INDEX
    Explanations

    directions and boundaries

    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
     dejected
    -1.67
     languid
    -1.48
    旆
    -1.44
     ऐसे
    -1.41
    ときの
    -1.40
     will
    -1.40
     actuels
    -1.38
     majeurs
    -1.35
     are
    -1.34
    たびに
    -1.34
    POSITIVE LOGITS
     and
    1.92
    ↵↵
    1.57
    ']='
    1.53
     about
    1.45
     pulseras
    1.41
     seguras
    1.35
     pestañas
    1.32
    ");
    1.31
     \
    1.30
     lectores
    1.22
    Activations Density 0.054%

    No Known Activations