© 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. 104608
    Prev
    Next
    INDEX
    Explanations

    programming constructs and identifiers

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

    The neuron fires on programming identifiers (variable, function, and module names) and related code tokens.

    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
     yanlış
    -0.97
     realmente
    -0.96
     télécharge
    -0.94
    jona
    -0.93
    στα
    -0.92
     松
    -0.90
     abierta
    -0.89
     months
    -0.88
    目前
    -0.88
     linguri
    -0.88
    POSITIVE LOGITS
    That
    0.93
    それを
    0.88
    finement
    0.84
     braun
    0.84
     or
    0.81
     claimant
    0.80
    みなさま
    0.79
     Polsek
    0.79
    統領
    0.79
    瞬間
    0.79
    Activations Density 0.004%

    No Known Activations