© 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. 22-GEMMASCOPE-RES-131K
    7. 16275
    Prev
    Next
    INDEX
    Explanations

    code syntax for parentheses and quotes

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

    The neuron never activates (it does not detect any particular token pattern).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     and
    -1.59
    gettyimages
    -1.52
     it
    -1.45
    providedIn
    -1.39
     Each
    -1.30
    shutterstock
    -1.29
     Umgang
    -1.23
     Many
    -1.23
     After
    -1.20
     If
    -1.17
    POSITIVE LOGITS
    </strong>
    1.57
    èt
    1.24
     ARIZONA
    1.23
    朥
    1.23
    焢
    1.20
    孕妇
    1.19
     ممکن
    1.17
     VERTICAL
    1.13
    Appellants
    1.12
    「
    1.12
    Activations Density 0.005%

    No Known Activations