© 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. 10-GEMMASCOPE-RES-131K
    7. 111023
    Prev
    Next
    INDEX
    Explanations

    added or contributing

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

    The neuron responds to numerical statistics and figures (e.g. point totals, scores, dates) 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_10/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
     it
    -1.50
    ௅
    -1.50
     acondicionado
    -1.46
     how
    -1.43
     musíte
    -1.40
     máte
    -1.35
     fantástico
    -1.34
     véritable
    -1.33
     biały
    -1.32
    ISHMENT
    -1.31
    POSITIVE LOGITS
     another
    1.45
    }
    1.30
     tabac
    1.27
    merkung
    1.27
     厂家
    1.26
     bret
    1.23
     furi
    1.22
    特别
    1.22
     weber
    1.22
    その
    1.20
    Activations Density 0.010%

    No Known Activations