© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35657
    Prev
    Next
    INDEX
    Explanations

    programming types and declarations

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

    This neuron activates on programming language type names (return types or data-type specifiers).

    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
     Juillet
    -1.05
    </em>
    -1.05
     intenção
    -0.98
     estação
    -0.96
    Series
    -0.96
     indústria
    -0.95
     замет
    -0.94
     estadia
    -0.94
    msgTypes
    -0.94
     igreja
    -0.94
    POSITIVE LOGITS
     of
    1.36
     from
    1.31
     but
    1.21
    Inhalts
    1.16
    Beskrivelse
    1.15
     in
    1.06
     although
    1.06
    معرفی
    1.05
     or
    1.02
    Składniki
    1.02
    Activations Density 0.005%

    No Known Activations