© 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. 68233
    Prev
    Next
    INDEX
    Explanations

    comparison and similarity

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

    The neuron preferentially activates on medium‐frequency content words (neither super common function words nor very rare terms).

    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
     both
    -0.94
     at
    -0.93
     sehr
    -0.91
     sowohl
    -0.88
     причем
    -0.87
     दोनों
    -0.87
    use
    -0.85
    ፍ
    -0.83
     ese
    -0.83
     whose
    -0.82
    POSITIVE LOGITS
     similarly
    1.41
    comparable
    1.41
     comparison
    1.31
     comparable
    1.30
     مشابه
    1.23
     confronto
    1.19
     similar
    1.19
     Similarly
    1.15
     certamente
    1.15
    éto
    1.13
    Activations Density 0.061%

    No Known Activations