© 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. 109035
    Prev
    Next
    INDEX
    Explanations

    body language and expressions

    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
    chlor
    -0.87
    moires
    -0.86
    onium
    -0.82
    oning
    -0.76
     zp
    -0.76
     jouant
    -0.74
     воспомина
    -0.73
    viertel
    -0.72
    pano
    -0.72
    ToolTip
    -0.72
    POSITIVE LOGITS
     body
    3.84
     facial
    3.34
    body
    2.78
     Body
    2.67
     Facial
    2.63
     gestures
    2.61
    facial
    2.58
    Body
    2.48
     BODY
    2.47
    Facial
    2.41
    Activations Density 0.047%

    No Known Activations