© 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. 92757
    Prev
    Next
    INDEX
    Explanations

    Chem., Int. Ed

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

    numeric values in technical and programming contexts.

    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
    miche
    -0.75
    kale
    -0.72
    REMOV
    -0.68
    ු
    -0.67
     Caterina
    -0.67
     Lade
    -0.65
    Order
    -0.64
    菴
    -0.64
     Simons
    -0.63
     Clarinet
    -0.62
    POSITIVE LOGITS
     Pub
    0.68
     cultures
    0.68
     Rovers
    0.66
    ioon
    0.66
     Lord
    0.66
     cou
    0.65
    峻
    0.65
    Ārējās
    0.64
     Lett
    0.63
     nim
    0.62
    Activations Density 0.093%

    No Known Activations