© 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. 39713
    Prev
    Next
    INDEX
    Explanations

    programming data types

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

    The neuron fires strongly on code identifiers that denote data types (e.g. class, struct, typedef, or other type names).

    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
    8
    -1.23
    0
    -1.20
     natale
    -1.15
    7
    -1.14
    蜂蜜
    -1.14
    9
    -1.13
    一品
    -1.13
    だが
    -1.12
    5
    -1.11
    1
    -1.06
    POSITIVE LOGITS
     its
    1.52
     mindig
    1.44
     zvuky
    1.34
    の方に
    1.29
    __(/*!
    1.28
     THEIR
    1.27
    toDouble
    1.27
     répon
    1.26
     zí
    1.26
     altijd
    1.26
    Activations Density 0.018%

    No Known Activations