© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 86333
    Prev
    Next
    INDEX
    Explanations

    8 or 9 followed by punctuation

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

    The neuron strongly activates on isolated single‐digit number tokens (e.g. “8” or “9”).

    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
    ladı
    -1.97
    糴
    -1.94
    the
    -1.88
     kickoff
    -1.84
     людей
    -1.80
    —
    -1.79
    頫
    -1.77
    Creating
    -1.77
     一个
    -1.75
     üblichen
    -1.72
    POSITIVE LOGITS
    ».
    2.08
    .).
    2.06
    }.
    2.06
    蜮
    2.00
    !)
    1.98
    ),"
    1.98
    ;
    
    
    1.96
    注意事
    1.93
    !).
    1.92
    })}
    1.90
    Activations Density 0.193%

    No Known Activations