© 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. 1747
    Prev
    Next
    INDEX
    Explanations

    extrajudicial; extradited; Adv. immunol

    np_acts-logits-general · gemini-2.5-flash-lite

    legal and copyright text, particularly license statements and terms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    кла
    -0.80
    EXPECT
    -0.73
    智
    -0.69
    secon
    -0.69
     ocupado
    -0.69
    ksy
    -0.68
    Intel
    -0.67
    律
    -0.67
     SRC
    -0.66
    Educación
    -0.66
    POSITIVE LOGITS
    Biographies
    0.71
     baili
    0.69
    GHI
    0.68
    혔
    0.66
    RCT
    0.66
    ACKNOWLEDGMENT
    0.66
    Giu
    0.66
     Oft
    0.65
    onais
    0.65
     indistingu
    0.64
    Activations Density 0.072%

    No Known Activations