© 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. 19708
    Prev
    Next
    INDEX
    Explanations

    Type followed by roman numerals

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

    This neuron detects classification labels—words like “Grade,” “Type,” or “Category” when used to name a numbered or named class.

    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
     for
    -2.23
     It
    -1.73
     sebagainya
    -1.54
    they
    -1.53
    👎
    -1.52
     He
    -1.52
    谕
    -1.52
    there
    -1.51
    ☹
    -1.50
                    
    -1.49
    POSITIVE LOGITS
    Här
    1.93
    leute
    1.84
    땃
    1.69
    Descriere
    1.66
    правления
    1.66
    sätzlich
    1.64
    Stap
    1.55
    CCIÓN
    1.55
     muerta
    1.51
    Assemblée
    1.48
    Activations Density 0.123%

    No Known Activations