© 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. 80975
    Prev
    Next
    INDEX
    Explanations

    type and kind specifiers

    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
    species
    -1.18
     species
    -0.95
     Species
    -0.94
    SPECIES
    -0.91
    Species
    -0.88
    pecies
    -0.80
    大帝
    -0.75
     imagined
    -0.75
     JT
    -0.73
     SPECIES
    -0.73
    POSITIVE LOGITS
     kind
    1.28
     type
    0.95
    parks
    0.82
     typeof
    0.82
    migrationBuilder
    0.82
    вшей
    0.81
    べし
    0.80
     groote
    0.80
     sort
    0.79
    byteArray
    0.79
    Activations Density 0.071%

    No Known Activations