© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92762
    Prev
    Next
    INDEX
    Explanations

    ordered published, for publication

    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
     jalur
    -0.88
     mitigating
    -0.79
     jembatan
    -0.79
     our
    -0.79
    ugges
    -0.78
    Esperamos
    -0.77
    正当
    -0.77
     suggest
    -0.75
    ξε
    -0.74
    élite
    -0.73
    POSITIVE LOGITS
     haplo
    0.82
    jdons
    0.81
    合并
    0.79
     Jessie
    0.79
    cektir
    0.79
    Lesson
    0.78
     would
    0.78
    olu
    0.77
     Wiltshire
    0.77
    Emily
    0.77
    Activations Density 0.002%

    No Known Activations