© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14066
    Prev
    Next
    INDEX
    Explanations

    specific word pairings

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

    The neuron activates on numeric tokens, especially sports‐related figures (points, minutes, scores, dates, and other stats).

    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
     казалось
    -0.90
    ülen
    -0.83
    ndel
    -0.82
     dança
    -0.80
     pinned
    -0.78
     diy
    -0.76
     Docs
    -0.76
     protetor
    -0.75
    给自己
    -0.75
    </thead>
    -0.73
    POSITIVE LOGITS
     from
    0.90
    ѐ
    0.85
     other
    0.83
    typescript
    0.78
     conejo
    0.78
    bij
    0.76
    优
    0.75
    posto
    0.75
     เห
    0.74
     suppose
    0.74
    Activations Density 0.002%

    No Known Activations