© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 923
    Prev
    Next
    INDEX
    Explanations

    Apache license 2.0

    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
    ovec
    -0.70
    Explosive
    -0.68
    Kud
    -0.68
     ECU
    -0.67
     peck
    -0.67
    Warriors
    -0.65
     representative
    -0.64
    Descrição
    -0.63
    Alfredo
    -0.62
     Lockhart
    -0.62
    POSITIVE LOGITS
    Renderer
    0.71
    specification
    0.69
    tool
    0.69
     Alters
    0.67
    กระ
    0.67
    广州
    0.67
    halation
    0.66
    Greek
    0.66
    POM
    0.65
    ങ്ങൾ
    0.65
    Activations Density 0.047%

    No Known Activations