© 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. 107442
    Prev
    Next
    INDEX
    Explanations

    formats, math, legal review

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

    The neuron fires on occurrences of the token “http,” i.e. it detects the literal string “http” in code or 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
    ူ
    -0.94
    帘
    -0.73
     پس
    -0.71
    hdessä
    -0.70
     じ
    -0.69
     таком
    -0.69
    boar
    -0.68
     Vanden
    -0.68
     civile
    -0.68
    grao
    -0.67
    POSITIVE LOGITS
     pegatinas
    0.81
     cadáver
    0.79
    န
    0.76
    amarin
    0.75
    Independent
    0.75
    )?;
    0.75
     Según
    0.74
    mmas
    0.73
    ányi
    0.72
     armé
    0.72
    Activations Density 0.006%

    No Known Activations