© 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. 108704
    Prev
    Next
    INDEX
    Explanations

    Calam, Kalam, Kamala, Calab, Calum

    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
    infra
    -0.79
    ಟ
    -0.78
    white
    -0.77
     Downloaded
    -0.70
    vä
    -0.68
     ow
    -0.68
    検証
    -0.67
     š
    -0.67
     Felicia
    -0.67
    ř
    -0.67
    POSITIVE LOGITS
     siihen
    0.73
     victor
    0.73
     olives
    0.73
     Moles
    0.73
     registrada
    0.72
    четов
    0.72
    不上
    0.71
     wives
    0.71
     Виктор
    0.70
     Kochen
    0.70
    Activations Density 0.021%

    No Known Activations