© 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. 79813
    Prev
    Next
    INDEX
    Explanations

    tf and tl abbreviations

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

    This neuron detects occurrences of the token “tf,” as used in code (e.g. TensorFlow or tf-prefixed identifiers).

    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
    isième
    -2.80
    s
    -2.61
    t
    -2.44
    warzys
    -2.36
    r
    -2.34
    ↵↵
    -2.31
    𖥦
    -2.17
    ↵
    -2.16
    的吧
    -2.16
    囖
    -2.14
    POSITIVE LOGITS
    If
    2.47
     surgir
    2.39
     nuestros
    2.38
     evidenced
    2.38
    ЖИ
    2.33
     creatively
    2.31
     また
    2.31
    にい
    2.19
    ти
    2.17
     encompass
    2.13
    Activations Density 0.028%

    No Known Activations