© 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. 59279
    Prev
    Next
    INDEX
    Explanations

    linebacker and receiver

    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
    ҍ
    -0.81
    rão
    -0.79
    mosis
    -0.77
    iany
    -0.76
    ënt
    -0.75
    Haute
    -0.75
    ärä
    -0.73
    зика
    -0.72
    setBorder
    -0.71
    ਿਆ
    -0.71
    POSITIVE LOGITS
     linebacker
    1.66
    LB
    1.30
     LB
    1.16
    dcmtk
    0.82
     receiver
    0.80
    backer
    0.76
    DL
    0.73
     receivers
    0.71
     backers
    0.69
     defensive
    0.69
    Activations Density 0.044%

    No Known Activations