© 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. 78880
    Prev
    Next
    INDEX
    Explanations

    subjects speaking

    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
    ⇪
    -1.00
     dénon
    -0.98
    ivity
    -0.95
    *}
    -0.94
    writing
    -0.93
    asked
    -0.92
    IVID
    -0.92
     Ask
    -0.92
    Apologies
    -0.91
    zheng
    -0.91
    POSITIVE LOGITS
     said
    4.06
     says
    2.47
     say
    2.06
     stated
    1.94
    said
    1.66
     saying
    1.54
     gesagt
    1.52
    Said
    1.46
     сказать
    1.41
     nói
    1.41
    Activations Density 0.003%

    No Known Activations