© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 98974
    Prev
    Next
    INDEX
    Explanations

    presence of

    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
    ."
    -1.81
    橚
    -1.63
     actionTypes
    -1.62
     jaja
    -1.59
    鸶
    -1.53
     fusil
    -1.52
     hdi
    -1.50
     langage
    -1.50
     ainfi
    -1.47
    各自
    -1.45
    POSITIVE LOGITS
    鸰
    1.65
     in
    1.62
     нужна
    1.61
     présence
    1.59
     piensa
    1.59
    謌
    1.48
    好不好
    1.45
     insists
    1.44
    说不定
    1.43
    他有
    1.42
    Activations Density 0.025%

    No Known Activations