© 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. 10-GEMMASCOPE-RES-131K
    7. 7677
    Prev
    Next
    INDEX
    Explanations

    places and specific entities

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

    The neuron activates most strongly on mentions of “SMA” (spinal muscular atrophy) and related terms (e.g. “muscular” in that context).

    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
    逦
    -3.11
    疇
    -2.61
    们的
    -2.61
    
    -2.56
    CHREIB
    -2.55
     незавер
    -2.55
    噚
    -2.52
    
    -2.50
    夀
    -2.50
    埸
    -2.50
    POSITIVE LOGITS
    0
    3.19
    “
    3.19
    1
    3.09
    '
    3.05
    a
    3.05
    _
    3.03
    6
    2.97
    9
    2.92
    8
    2.89
     dando
    2.86
    Activations Density 0.018%

    No Known Activations