© 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. 34-GEMMASCOPE-RES-131K
    7. 108570
    Prev
    Next
    INDEX
    Explanations

    returned or bounced messages

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

    The neuron fires strongly on numeric tokens (digits or numbers) 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
     setw
    -0.90
    íně
    -0.82
    setRequest
    -0.73
    élève
    -0.73
    ʑ
    -0.71
     vul
    -0.70
    JC
    -0.70
    ΙΑ
    -0.68
    क्स
    -0.67
     extracurricular
    -0.67
    POSITIVE LOGITS
     returned
    2.48
     bounced
    2.42
     bounce
    2.19
     bounces
    2.00
     Returned
    1.99
    returned
    1.91
     bouncing
    1.90
    bounce
    1.84
     Bounce
    1.83
    Bounce
    1.75
    Activations Density 0.032%

    No Known Activations