© 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. 87121
    Prev
    Next
    INDEX
    Explanations

    integer types in code

    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
     spis
    -0.83
    manner
    -0.83
    vature
    -0.76
     Parish
    -0.76
    reactivex
    -0.75
    шому
    -0.74
     communal
    -0.71
     parish
    -0.71
    avascript
    -0.70
     です
    -0.68
    POSITIVE LOGITS
     Goed
    0.80
    0.75
    ânea
    0.75
    Orsay
    0.74
     ilyen
    0.73
    ilot
    0.72
    聲音
    0.72
     §§
    0.72
    GetKeyDown
    0.71
    PHO
    0.71
    Activations Density 0.061%

    No Known Activations