© 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. 1359
    Prev
    Next
    INDEX
    Explanations

    Tom followed by specific words

    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
    надца
    -0.86
     Accueil
    -0.81
     akut
    -0.74
     Nieren
    -0.73
     anim
    -0.71
    商品は
    -0.70
     Général
    -0.69
     wani
    -0.69
     not
    -0.68
    Descripción
    -0.68
    POSITIVE LOGITS
    Tom
    1.88
     tom
    1.73
     Tom
    1.38
    tom
    1.34
    morrow
    1.26
    fool
    1.22
    ioka
    1.21
     توم
    1.17
     Том
    1.07
     Toms
    1.07
    Activations Density 0.026%

    No Known Activations