© 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. 33191
    Prev
    Next
    INDEX
    Explanations

    low or lower intensity

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

    The neuron is detecting short, high-frequency function tokens—small words like prepositions (“to,” “with”), pronouns (“it,” “they”), auxiliaries (“may”), and hyphens.

    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
     luminos
    -0.84
     insegu
    -0.76
     fertig
    -0.75
    логических
    -0.74
    γραμμα
    -0.72
     inequalities
    -0.71
     sentirse
    -0.69
     階
    -0.69
     situasi
    -0.68
     minera
    -0.67
    POSITIVE LOGITS
     low
    2.59
    low
    1.99
    Low
    1.94
     Low
    1.92
    低调
    1.91
     profile
    1.64
     LOW
    1.59
    低
    1.59
    LOW
    1.56
     quiet
    1.52
    Activations Density 0.019%

    No Known Activations