© 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. 6750
    Prev
    Next
    INDEX
    Explanations

    curl commands and names

    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
     atque
    -0.97
     leaning
    -0.81
    leaning
    -0.79
    meras
    -0.75
     usually
    -0.74
    Trama
    -0.74
     choose
    -0.74
    ísticas
    -0.74
     Cleaning
    -0.73
     with
    -0.73
    POSITIVE LOGITS
    RETURN
    1.00
    Return
    0.87
    ensivo
    0.86
    ního
    0.85
    FOLLOW
    0.82
     menge
    0.81
    Follow
    0.79
     PAST
    0.78
    ixed
    0.77
     RETURN
    0.77
    Activations Density 0.005%

    No Known Activations