© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74811
    Prev
    Next
    INDEX
    Explanations

    JavaScript function declarations

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

    The neuron flags identifiers where something is being defined or assigned—i.e. variable or function names on the left‐hand side of a declaration or “=” assignment.

    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
     of
    -1.66
     ,
    -1.60
     C
    -1.51
     -
    -1.48
     по
    -1.41
     EVERY
    -1.41
     ....
    -1.40
    -
    -1.40
    zyć
    -1.39
     M
    -1.38
    POSITIVE LOGITS
    蚰
    1.98
    𓆏
    1.92
    ſſen
    1.77
    鉏
    1.77
     westfalen
    1.64
     ventes
    1.63
     GRATIS
    1.62
    瞇
    1.57
     peluche
    1.55
     lampe
    1.55
    Activations Density 0.019%

    No Known Activations