© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103597
    Prev
    Next
    INDEX
    Explanations

    database adapter and connection

    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
    さまでした
    -0.81
     burlesque
    -0.73
    ㅘ
    -0.71
    ἴ
    -0.69
    rigan
    -0.69
    验
    -0.69
     epidermis
    -0.68
    encodeWith
    -0.67
    userdata
    -0.66
     ASF
    -0.66
    POSITIVE LOGITS
    connection
    1.05
    arel
    0.85
     connection
    0.84
    *}{
    0.82
    quoted
    0.81
    TAR
    0.80
     tandis
    0.78
    fiddle
    0.78
     Shari
    0.77
     Connection
    0.76
    Activations Density 0.037%

    No Known Activations