© 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. 97975
    Prev
    Next
    INDEX
    Explanations

    bibliography entries

    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
    ště
    -0.72
    绶
    -0.71
     λα
    -0.71
    кога
    -0.69
    放在
    -0.68
     reincarnation
    -0.68
    canos
    -0.67
    ielli
    -0.67
    そうです
    -0.65
    ramienta
    -0.65
    POSITIVE LOGITS
    mage
    0.81
    ету
    0.81
    azawa
    0.81
    ിക്ക
    0.75
    テル
    0.74
    που
    0.74
    sections
    0.73
    Address
    0.73
    InstanceOf
    0.73
     Ait
    0.72
    Activations Density 0.023%

    No Known Activations