© 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. 32926
    Prev
    Next
    INDEX
    Explanations

    verbal fluency and memory

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     aparece
    -0.68
     XMLHttpRequest
    -0.67
    strto
    -0.67
    fom
    -0.66
    OPO
    -0.65
    મે
    -0.65
     kualitas
    -0.65
    ອ
    -0.65
    makeText
    -0.65
    忑
    -0.64
    POSITIVE LOGITS
     fluent
    4.50
     fluency
    3.84
     flu
    3.61
    fluent
    3.39
     Fluent
    3.39
    Fluent
    3.19
     Flu
    3.16
    flu
    3.09
    Flu
    2.97
     FLU
    2.66
    Activations Density 0.050%

    No Known Activations