© 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. 34-GEMMASCOPE-RES-131K
    7. 62999
    Prev
    Next
    INDEX
    Explanations

    ambition and scale

    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_34/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
    rdag
    -0.93
     mę
    -0.78
    PUESTA
    -0.77
    醐
    -0.75
     komment
    -0.75
     viñ
    -0.74
     tía
    -0.74
     ситуации
    -0.73
     sobres
    -0.73
     situations
    -0.72
    POSITIVE LOGITS
     ambitious
    5.25
     ambition
    4.22
     ambitions
    3.89
     ambiti
    3.36
     Ambition
    2.83
    ambition
    2.69
     bold
    2.59
    amb
    2.30
     ам
    2.30
     daring
    2.28
    Activations Density 0.068%

    No Known Activations