© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66725
    Prev
    Next
    INDEX
    Explanations

    bold and bolts

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

    The neuron strongly activates on occurrences of the word “Bold,” effectively detecting references to bold formatting or bold‐styled 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_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
     большое
    -2.67
     hermosas
    -2.67
    ญี่ป
    -2.61
    sonaro
    -2.55
    </h5>
    -2.48
     impresionantes
    -2.44
    箩
    -2.38
     espectaculares
    -2.33
     preciosas
    -2.33
    wiście
    -2.27
    POSITIVE LOGITS
    1
    4.00
    2
    3.77
    5
    3.66
    4
    3.42
    6
    3.31
    8
    3.30
    3
    3.23
    7
    3.19
     the
    2.73
    釭
    2.70
    Activations Density 0.014%

    No Known Activations