© 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. 15486
    Prev
    Next
    INDEX
    Explanations

    TypeError:

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

    This neuron fires on code identifiers—names of functions, methods, or other programming symbols.

    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
    裥
    -1.88
    several
    -1.72
    蛱
    -1.71
    鼉
    -1.71
    different
    -1.59
     verschillende
    -1.58
    ’;
    -1.45
     semelh
    -1.45
     różnych
    -1.45
     mereka
    -1.43
    POSITIVE LOGITS
     preventing
    1.55
     started
    1.52
     focused
    1.41
     on
    1.35
     undeniably
    1.33
     begins
    1.31
     might
    1.30
     has
    1.30
     trying
    1.30
     before
    1.29
    Activations Density 0.000%

    No Known Activations