© 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. 119076
    Prev
    Next
    INDEX
    Explanations

    court cases and licenses

    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
    attrib
    -0.70
     arousal
    -0.69
    Ids
    -0.66
    ReLU
    -0.66
     tip
    -0.62
    Orientation
    -0.62
    ime
    -0.62
     sly
    -0.61
    Bg
    -0.61
    assertNotNull
    -0.60
    POSITIVE LOGITS
     Sury
    0.82
    Cite
    0.69
    pade
    0.69
    マヨ
    0.68
    帑
    0.68
    GeneratedCode
    0.67
     Sonnen
    0.66
    ticle
    0.66
     pah
    0.65
     beaded
    0.65
    Activations Density 0.079%

    No Known Activations