© 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. 70953
    Prev
    Next
    INDEX
    Explanations

    uneasy, restless, or edgy states

    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
    訁
    -1.84
     Öffnen
    -1.71
     جاء
    -1.70
     入り
    -1.68
    实行
    -1.67
     respective
    -1.66
    
    -1.66
     equilíbrio
    -1.64
     يبدو
    -1.58
     adaptées
    -1.58
    POSITIVE LOGITS
     et
    1.86
     in
    1.80
    ina
    1.59
    ↵↵
    1.58
    Harmful
    1.50
     Че
    1.46
    ens
    1.45
     about
    1.44
    Colleen
    1.42
    pherical
    1.41
    Activations Density 0.023%

    No Known Activations