© 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. 107342
    Prev
    Next
    INDEX
    Explanations

    specific modifiers

    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
     fahr
    -0.81
    kori
    -0.74
     protectora
    -0.73
     Strongly
    -0.72
     uporab
    -0.71
     トレー
    -0.71
     fashioned
    -0.71
     vielleicht
    -0.70
    或許
    -0.70
    ✑
    -0.70
    POSITIVE LOGITS
     gravity
    1.37
     Gravity
    1.28
    gravity
    1.16
    Gravity
    1.15
    Specific
    0.94
     специфи
    0.93
     Specific
    0.90
     specific
    0.90
     IgE
    0.89
     epithet
    0.88
    Activations Density 0.041%

    No Known Activations