© 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. 12333
    Prev
    Next
    INDEX
    Explanations

    including headers

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

    `#include` preprocessor directives in source code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    _
    -2.14
     indicate
    -2.06
    ?"
    -2.00
     productivo
    -1.95
     bezeichnen
    -1.89
    ﾀ
    -1.88
     oversee
    -1.86
     pouvez
    -1.85
    ’
    -1.84
     protect
    -1.83
    POSITIVE LOGITS
     paa
    2.31
    赑
    2.19
    “)
    2.19
    馓
    2.03
     vorm
    2.02
     noten
    2.02
     itſelf
    2.00
     vano
    1.97
     ney
    1.95
     sprüche
    1.95
    Activations Density 0.032%

    No Known Activations