© 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. 2669
    Prev
    Next
    INDEX
    Explanations

    Functional brain imaging

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

    user interface elements in iOS settings and configuration instructions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    Unlike
    -0.78
    签约
    -0.74
    لول
    -0.74
    綁
    -0.73
     EVERY
    -0.72
     obu
    -0.71
     gave
    -0.71
     became
    -0.68
    Aroma
    -0.68
     bağ
    -0.68
    POSITIVE LOGITS
    ται
    0.88
    IBarButtonItem
    0.87
     Subs
    0.84
    MemoryWarning
    0.84
    icked
    0.83
    reduce
    0.81
     Wert
    0.80
    emp
    0.79
     Siri
    0.78
     വ
    0.77
    Activations Density 0.027%

    No Known Activations