© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 69
    Prev
    Next
    INDEX
    Explanations

    list.setOnItemClickedListener

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

    This neuron flags lines containing leading‐whitespace (indentation) in code blocks.

    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
     those
    -1.48
     from
    -1.42
     of
    -1.42
    ୈ
    -1.39
    czerw
    -1.38
    ;
    
    
    -1.32
    روابط
    -1.29
     ligiloj
    -1.29
     on
    -1.28
    hydrogenase
    -1.28
    POSITIVE LOGITS
     horrid
    1.44
     astounding
    1.42
     bizarre
    1.35
     diversos
    1.34
     monstrous
    1.32
     insanely
    1.32
     astonishing
    1.28
     wondrous
    1.26
     пять
    1.25
     следующее
    1.24
    Activations Density 0.233%

    No Known Activations