© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128352
    Prev
    Next
    INDEX
    Explanations

    giving praise or making announcements

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

    The neuron fires on informal “shout‐out” acknowledgments (e.g. “shout out to…” or “shout-outs go to…”).

    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
     estos
    -1.90
    "
    -1.85
     all
    -1.85
     y
    -1.74
     essa
    -1.70
    ｿ
    -1.70
     wichtig
    -1.70
     donde
    -1.68
     With
    -1.64
     start
    -1.63
    POSITIVE LOGITS
     unſ
    2.06
    垆
    2.02
    .";
    1.98
    蟊
    1.97
     WRITE
    1.97
    
    1.95
    ⢓
    1.91
     canin
    1.91
     valentín
    1.89
    cended
    1.88
    Activations Density 0.004%

    No Known Activations