© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98160
    Prev
    Next
    INDEX
    Explanations

    body parts and actions

    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
     steeper
    -0.81
    Helmet
    -0.80
     pedicure
    -0.74
     Anthem
    -0.73
     Brill
    -0.70
     cleats
    -0.69
    hatenablog
    -0.69
    ớp
    -0.68
    thinkable
    -0.66
    derby
    -0.66
    POSITIVE LOGITS
     arm
    4.72
     arms
    4.41
    arm
    3.30
    arms
    3.28
     Arm
    3.06
     Arms
    2.95
    Arm
    2.95
    Arms
    2.92
     brazo
    2.84
    臂
    2.64
    Activations Density 0.051%

    No Known Activations