© 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. 44523
    Prev
    Next
    INDEX
    Explanations

    supported

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

    The neuron activates on occurrences of the word “support” (and its inflected forms like “supports” or “supported”).

    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
     It
    -1.46
     out
    -1.46
     one
    -1.39
    dä
    -1.39
     lahko
    -1.38
     partes
    -1.34
     this
    -1.34
     probably
    -1.32
    section
    -1.30
     posible
    -1.27
    POSITIVE LOGITS
    擽
    1.51
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.38
     اکنون
    1.36
     deliciously
    1.36
    UNIVERSIDAD
    1.35
    袿
    1.35
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.34
    cracy
    1.32
    のかも
    1.31
     permettant
    1.27
    Activations Density 0.076%

    No Known Activations