© 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. 128224
    Prev
    Next
    INDEX
    Explanations

    topics and specific terms

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

    The neuron activates on technical computing jargon—especially programming language names, code commands, and related API or system-level terms.

    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
     with
    -1.72
     постоянно
    -1.43
     but
    -1.41
     S
    -1.40
    産の
    -1.38
     P
    -1.36
    C
    -1.34
     out
    -1.33
     R
    -1.32
     одной
    -1.32
    POSITIVE LOGITS
     that
    1.85
     you
    1.80
     boute
    1.72
     rése
    1.70
     inond
    1.63
     multicolore
    1.58
     also
    1.55
    ⿵
    1.55
    ⤒
    1.54
     vostre
    1.53
    Activations Density 0.473%

    No Known Activations