© 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. 21383
    Prev
    Next
    INDEX
    Explanations

    closing brace }

    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
    I
    -1.77
    -
    -1.74
     renowned
    -1.73
     stel
    -1.69
    のだろうか
    -1.66
     ajouter
    -1.64
     uyt
    -1.63
     eene
    -1.61
     hemd
    -1.60
     intertw
    -1.59
    POSITIVE LOGITS
     primeiras
    1.84
     mesmas
    1.81
     águas
    1.67
     because
    1.66
     —
    1.51
     preferências
    1.48
    …！
    1.46
     próprias
    1.40
     fotógrafo
    1.39
     verduras
    1.38
    Activations Density 0.001%

    No Known Activations