© 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. 21541
    Prev
    Next
    INDEX
    Explanations

    sentences with introductory phrases

    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
    戗
    -2.86
    鼍
    -2.81
     italiens
    -2.75
     abiye
    -2.70
    鱨
    -2.67
    錾
    -2.66
     tatou
    -2.63
    glück
    -2.61
     parachoque
    -2.59
    
    -2.59
    POSITIVE LOGITS
     There
    3.23
     and
    3.23
     However
    3.09
     While
    3.02
    This
    2.95
     If
    2.89
    ↵↵
    2.80
     Though
    2.78
     in
    2.78
     Although
    2.77
    Activations Density 1.177%

    No Known Activations