© 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. 32278
    Prev
    Next
    INDEX
    Explanations

    Free Software Foundation version

    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
    zeichnung
    -0.89
     המס
    -0.77
     furthering
    -0.72
    Galax
    -0.71
     Grave
    -0.71
     wishing
    -0.71
     людям
    -0.70
    warrant
    -0.70
    諫
    -0.69
     helping
    -0.69
    POSITIVE LOGITS
     загряз
    0.73
     trám
    0.72
    end
    0.71
     acabó
    0.70
    releases
    0.69
     mediator
    0.69
    ROOMS
    0.69
     describir
    0.68
     sympathize
    0.68
    がない
    0.68
    Activations Density 0.039%

    No Known Activations