© 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. 10-GEMMASCOPE-RES-131K
    7. 67163
    Prev
    Next
    INDEX
    Explanations

    Panasonic, progesterone, propane, oregano, Polaris

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

    brand names and scientific/chemical terms.

    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_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
    pecabe
    -2.81
    colgante
    -2.77
    夘
    -2.56
    𖣔
    -2.55
    brinco
    -2.52
     погиб
    -2.50
    archiwizowane
    -2.48
     andere
    -2.45
    ⃢
    -2.44
    
    -2.44
    POSITIVE LOGITS
    s
    2.77
    ization
    2.64
    one
    2.63
    b
    2.63
    n
    2.59
    self
    2.45
    er
    2.42
    just
    2.41
    There
    2.38
    Some
    2.38
    Activations Density 0.019%

    No Known Activations