© 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. 34-GEMMASCOPE-RES-131K
    7. 63287
    Prev
    Next
    INDEX
    Explanations

    spelling common suffixes like 'elds', 'icant', 'ine'

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

    The neuron strongly activates on number tokens and numeric expressions (e.g. digits, multi‐digit numbers, and numeric sequences) in the text.

    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
    ‎
    -0.88
     ‎
    -0.84
    -​
    -0.80
     
    -0.79
    illar
    -0.75
     Feast
    -0.74
    žil
    -0.74
    iala
    -0.73
    cisme
    -0.71
    Luiz
    -0.70
    POSITIVE LOGITS
     rst
    1.03
     eld
    0.90
    rst
    0.88
     bene
    0.82
    ❼
    0.81
    fi
    0.80
    Ｙ
    0.77
     fi
    0.76
     كم
    0.76
    fl
    0.75
    Activations Density 0.284%

    No Known Activations