© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107941
    Prev
    Next
    INDEX
    Explanations

    vim tab settings

    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
    ürzt
    -0.83
    瘫
    -0.82
    perfusion
    -0.81
     Terrain
    -0.81
    Captcha
    -0.81
     uintptr
    -0.80
    washingtonpost
    -0.78
    CHRON
    -0.77
    amental
    -0.76
    opardi
    -0.76
    POSITIVE LOGITS
     tab
    1.15
     tabs
    1.01
    tab
    1.00
    tabs
    0.93
    Tabs
    0.92
     Tab
    0.83
     expand
    0.82
    Tab
    0.82
     Ind
    0.82
    smart
    0.81
    Activations Density 0.078%

    No Known Activations