© 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. 76783
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
     abgesch
    -0.70
    zitter
    -0.68
     Kessler
    -0.66
    corporated
    -0.66
     Aix
    -0.65
    ksamkeit
    -0.65
    scu
    -0.65
     registrados
    -0.65
    alties
    -0.65
    assign
    -0.64
    POSITIVE LOGITS
    RIB
    0.77
    kém
    0.75
     forever
    0.74
    CATALOG
    0.71
     Puritan
    0.71
    hli
    0.70
    rowning
    0.70
    yonel
    0.70
    נסת
    0.69
     BBA
    0.69
    Activations Density 0.057%

    No Known Activations