© 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. 10-GEMMASCOPE-RES-131K
    4. 23973
    Prev
    Next
    INDEX
    Explanations

    programming libraries and frameworks

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

    This neuron fires on technical library or package identifiers (e.g. “data,” “cloud,” “util,” “module,” “rest,” “drf”) in code and configuration.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    主要是
    -1.93
    訁
    -1.81
     WITH
    -1.71
    );
    -1.65
     Membuat
    -1.63
    大多
    -1.61
     nenhuma
    -1.60
    azzo
    -1.59
     стоко
    -1.59
     ratusan
    -1.58
    POSITIVE LOGITS
    遊んで
    1.45
    —
    1.40
    however
    1.36
    すば
    1.34
    -
    1.30
    だら
    1.29
    入った
    1.28
     implan
    1.28
    er
    1.27
    楕
    1.25
    Activations Density 0.003%

    No Known Activations