© 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. 31297
    Prev
    Next
    INDEX
    Explanations

    history and histology

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

    The word "history" or "historical" and related terms (especially when used in academic or medical 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
    Odd
    -0.88
     Odd
    -0.80
    σεις
    -0.75
     hjæl
    -0.71
     глазами
    -0.70
    Od
    -0.70
    onset
    -0.69
    љ
    -0.68
    प्र
    -0.68
    \]
    -0.68
    POSITIVE LOGITS
     history
    3.28
     story
    2.94
    story
    2.92
     storia
    2.89
     historia
    2.89
    histoire
    2.84
     história
    2.78
    history
    2.67
     истории
    2.66
     Geschichte
    2.59
    Activations Density 0.046%

    No Known Activations