© 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. 70247
    Prev
    Next
    INDEX
    Explanations

    early literacy and numeracy

    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
    msup
    -0.83
     adolescent
    -0.81
    ঐ
    -0.80
    內容
    -0.80
     Adoles
    -0.77
     sred
    -0.77
    겼
    -0.75
    нились
    -0.74
    spiegel
    -0.74
     Fad
    -0.74
    POSITIVE LOGITS
     letter
    1.96
     letters
    1.95
     alphabet
    1.73
     numbers
    1.56
     ABC
    1.52
     alphabets
    1.52
     counting
    1.49
     Letter
    1.48
     Letters
    1.38
     reading
    1.35
    Activations Density 0.025%

    No Known Activations