© 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. 34-GEMMASCOPE-RES-131K
    7. 23844
    Prev
    Next
    INDEX
    Explanations

    tuning in

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

    The neuron detects occurrences of the “tune in” family of phrases (e.g. tune in, tuned in, tuning in) indicating viewers starting or watching a broadcast.

    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
    errcode
    -0.95
    s
    -0.94
    統計
    -0.94
     =======
    -0.91
     зак
    -0.88
     был
    -0.85
    inės
    -0.85
     scound
    -0.85
     ehemalige
    -0.85
     BorderSide
    -0.85
    POSITIVE LOGITS
    tune
    2.03
     tuned
    2.03
     tuning
    2.00
    tuning
    1.88
     tune
    1.82
    Tune
    1.80
     Tune
    1.78
    TUN
    1.63
     tunes
    1.62
    tuned
    1.57
    Activations Density 0.008%

    No Known Activations