© 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. 39862
    Prev
    Next
    INDEX
    Explanations

    technical and organizational terms

    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
    蚰
    -1.85
     actualité
    -1.70
     erhi
    -1.70
    
    -1.61
     jezt
    -1.59
     utilisant
    -1.59
     uniquement
    -1.56
    Ⴀ
    -1.56
     actuel
    -1.55
     prefier
    -1.55
    POSITIVE LOGITS
     While
    2.05
     blissful
    2.03
     from
    2.03
     cheery
    1.93
     multifaceted
    1.89
     for
    1.79
     exuberant
    1.72
    ０
    1.72
     obnoxious
    1.67
     como
    1.66
    Activations Density 0.082%

    No Known Activations