© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98180
    Prev
    Next
    INDEX
    Explanations

    <?php code

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

    The neuron responds strongly to numeric literals—especially version, build, or other digits embedded in comments.

    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
     condicion
    -0.91
     الحالة
    -0.88
    çou
    -0.84
    днако
    -0.84
     ј
    -0.81
     юби
    -0.80
    trá
    -0.78
     samlet
    -0.77
    matous
    -0.77
    cerr
    -0.77
    POSITIVE LOGITS
     sats
    0.81
     periódicos
    0.81
     bezpieczeństwa
    0.72
     esso
    0.71
     faptul
    0.70
     into
    0.69
    手間
    0.69
     man
    0.68
    נג
    0.68
     вниз
    0.68
    Activations Density 0.000%

    No Known Activations