© 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. 81056
    Prev
    Next
    INDEX
    Explanations

    instagram stories

    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
    uar
    -0.72
    itec
    -0.71
     uintptr
    -0.69
     Pante
    -0.69
    assertArray
    -0.68
    ി
    -0.68
     balanceOf
    -0.67
     Ao
    -0.66
    升级
    -0.66
    затор
    -0.66
    POSITIVE LOGITS
     stories
    4.56
     Stories
    4.16
    Stories
    3.83
    stories
    3.75
     story
    3.70
     Story
    3.41
    Story
    3.22
     STORIES
    3.14
    story
    3.08
     STORY
    2.72
    Activations Density 0.015%

    No Known Activations