© 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. 108390
    Prev
    Next
    INDEX
    Explanations

    project configurations

    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
    וֹ
    -0.75
    春天
    -0.71
     břez
    -0.70
    fren
    -0.69
     etk
    -0.69
    raja
    -0.69
     AGRICULTURE
    -0.68
    Ѵ
    -0.68
     devriez
    -0.68
     acús
    -0.68
    POSITIVE LOGITS
     TRI
    0.73
     Amb
    0.73
     Turing
    0.71
     Ny
    0.68
     Olympian
    0.66
     Digest
    0.66
     Mailing
    0.66
     Hay
    0.65
     Dig
    0.65
     Angels
    0.64
    Activations Density 0.059%

    No Known Activations