© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81232
    Prev
    Next
    INDEX
    Explanations

    Angular component syntax

    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
     żeby
    -0.79
    descriptors
    -0.76
     чтобы
    -0.74
    rices
    -0.69
    scrollTo
    -0.68
    entum
    -0.68
    Divider
    -0.68
    ubehör
    -0.68
    getResource
    -0.67
    нимание
    -0.66
    POSITIVE LOGITS
     bailando
    0.82
    stato
    0.79
     Tratt
    0.76
     Rens
    0.74
    渺
    0.73
    migrationBuilder
    0.72
    issionais
    0.71
    ďte
    0.71
     *
    0.70
    ADOW
    0.68
    Activations Density 0.005%

    No Known Activations