© 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. 59206
    Prev
    Next
    INDEX
    Explanations

    numbers and *as published*

    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
     Or
    -1.05
     Или
    -0.94
    Or
    -0.92
    OrCreate
    -0.82
    getOr
    -0.81
     или
    -0.73
    inada
    -0.72
     或
    -0.71
    Statements
    -0.69
     mitosis
    -0.69
    POSITIVE LOGITS
     ten
    1.17
    Ten
    1.16
    十
    1.10
     Ten
    1.06
     十
    0.87
     Tenth
    0.82
     TEN
    0.73
    十分
    0.73
    ten
    0.73
    tenth
    0.71
    Activations Density 0.257%

    No Known Activations