© 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. 82931
    Prev
    Next
    INDEX
    Explanations

    configuration file keys

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

    The neuron fires on standalone capitalized identifier tokens—e.g. class, model, or field names in code (CamelCase or PascalCase fragments).

    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
     these
    -1.16
     besonders
    -1.02
     those
    -1.00
     there
    -0.97
     Those
    -0.96
    faring
    -0.95
     There
    -0.94
    Curios
    -0.94
     pries
    -0.92
     vermutlich
    -0.92
    POSITIVE LOGITS
    tigs
    1.20
    Jereo
    1.09
    eniging
    1.09
     Verhältnis
    1.09
    ها
    1.08
    或
    1.06
     чехол
    1.05
     conferencias
    1.05
     talleres
    1.05
     gimnasio
    1.05
    Activations Density 0.052%

    No Known Activations