© 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. 80935
    Prev
    Next
    INDEX
    Explanations

    children's play and learning

    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
     Decide
    -0.74
    कु
    -0.71
    achal
    -0.67
     decide
    -0.67
    ۷
    -0.66
    Tack
    -0.64
    spora
    -0.64
     jum
    -0.64
    रा
    -0.63
    ㅓ
    -0.63
    POSITIVE LOGITS
     toys
    1.07
     cognition
    1.00
     children
    0.94
     ASTM
    0.94
     intellectual
    0.94
     Cognition
    0.93
     divert
    0.92
     Intellectual
    0.89
     play
    0.88
    logica
    0.86
    Activations Density 0.007%

    No Known Activations