© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58722
    Prev
    Next
    INDEX
    Explanations

    cycling races and champions

    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
     OECD
    -0.79
     фра
    -0.78
    ibrary
    -0.77
     merveille
    -0.76
     apprécier
    -0.75
    ReusableCell
    -0.74
     begu
    -0.73
     rune
    -0.73
    ounid
    -0.72
    voyez
    -0.72
    POSITIVE LOGITS
     crit
    0.92
    Primes
    0.83
    crit
    0.83
     criter
    0.81
    lgica
    0.80
    áles
    0.79
    Fondo
    0.77
     moléculas
    0.76
    児
    0.75
    Crit
    0.74
    Activations Density 0.030%

    No Known Activations