© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109368
    Prev
    Next
    INDEX
    Explanations

    arms or arm extended

    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
     程序
    -0.81
     vreme
    -0.78
     fume
    -0.77
    酮
    -0.76
    ukunft
    -0.76
     setColor
    -0.76
     kuu
    -0.75
    nitř
    -0.74
     findBy
    -0.74
     Kapital
    -0.74
    POSITIVE LOGITS
     arm
    4.97
     arms
    4.69
    arm
    3.63
    arms
    3.47
     Arms
    3.22
     Arm
    3.13
    Arm
    3.09
    Arms
    3.08
     ARMS
    2.38
     ARM
    2.33
    Activations Density 0.023%

    No Known Activations