© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 58963
    Prev
    Next
    INDEX
    Explanations

    steps and sequences

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

    This neuron responds to detailed biomechanical descriptions of coordinated body movements and joint actions (e.g. elbow straightening, shoulder rotation) in activities like pitching.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    がこの
    -1.25
     enligt
    -1.24
    はこの
    -1.24
    Millions
    -1.20
     onları
    -1.18
    küche
    -1.16
     ramb
    -1.14
    トッピング
    -1.12
    Ṃ
    -1.10
     эту
    -1.09
    POSITIVE LOGITS
     cuando
    1.60
     when
    1.48
     can
    1.43
     where
    1.30
     όταν
    1.25
     while
    1.20
     algunos
    1.19
     patru
    1.18
     your
    1.18
     I
    1.18
    Activations Density 0.056%

    No Known Activations