© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73294
    Prev
    Next
    INDEX
    Explanations

    conditional logic: else, else if, elif

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

    The neuron activates on “else” (and “elseif”) keywords in code, i.e. it detects alternative-branch statements.

    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
    d
    -1.20
     also
    -1.20
     now
    -1.09
    かもしれませんが
    -1.06
    などが
    -1.06
    MENAFN
    -1.05
    がある
    -1.04
    でしょうね
    -1.04
    队长
    -1.01
    f
    -1.01
    POSITIVE LOGITS
    ⟹
    1.49
     berdua
    1.46
    {}
    
    1.42
    𖣘
    1.37
    cccccccc
    1.25
     GRATU
    1.25
    ◔
    1.24
     beschä
    1.24
    $\%$
    1.23
    andafter
    1.23
    Activations Density 0.001%

    No Known Activations