© 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. 33321
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

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

    This neuron detects code comparison and function‐call patterns—especially strict equality checks (===) and test/call method invocations with parentheses.

    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
     作り方
    -1.17
     definiti
    -1.13
    various
    -1.12
     lanterna
    -1.12
    ି
    -1.11
     différentes
    -1.09
     diriger
    -1.08
    他们
    -1.07
    ἥ
    -1.05
     ここ
    -1.04
    POSITIVE LOGITS
     or
    1.90
     your
    1.73
     in
    1.29
     this
    1.13
     at
    1.10
     you
    1.04
     kept
    1.04
    \!\
    1.02
     noteworthy
    1.02
     good
    1.02
    Activations Density 0.001%

    No Known Activations