© 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. 58269
    Prev
    Next
    INDEX
    Explanations

    single body part

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires strongly on mentions of “one hand,” i.e. references to using a single hand.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     سيارة
    -0.79
    ベー
    -0.70
     hag
    -0.69
    CommandType
    -0.69
    setLayoutParams
    -0.68
     Stiftung
    -0.68
     tachycardia
    -0.68
    Краси
    -0.68
     inkl
    -0.68
    ними
    -0.68
    POSITIVE LOGITS
     arm
    2.06
     eye
    1.88
     hand
    1.86
     leg
    1.84
     ear
    1.52
     foot
    1.52
     legs
    1.29
    eye
    1.25
     knee
    1.24
    arm
    1.22
    Activations Density 0.058%

    No Known Activations