© 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. 34-GEMMASCOPE-RES-131K
    4. 91292
    Prev
    Next
    INDEX
    Explanations

    generic type constraints

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

    This neuron responds to the appearance of generic type parameters and their constraints (e.g. single‐letter type variables like T, U, g, e and “where” clauses) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     who
    -1.00
    \}$.
    -0.88
     recrystal
    -0.76
    เพราะ
    -0.75
    зыка
    -0.74
     hit
    -0.72
    жих
    -0.71
    )}$.
    -0.69
    ニュース
    -0.66
    fili
    -0.66
    POSITIVE LOGITS
    where
    1.28
     wherever
    1.25
     WHERE
    1.11
    WHERE
    1.02
     فيه
    1.00
     فيها
    0.99
     where
    0.98
     Where
    0.95
    其中
    0.94
    Where
    0.84
    Activations Density 0.014%

    No Known Activations