© 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. 48725
    Prev
    Next
    INDEX
    Explanations

    treatment options, guidelines, insights

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

    academic or medical journal formatting elements such as citations, headers, and publication information.

    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
    muse
    -0.88
    lllllllll
    -0.84
     pasang
    -0.82
     demandas
    -0.81
     jewels
    -0.81
     إل
    -0.78
     adopté
    -0.77
    uesta
    -0.75
    lllllll
    -0.75
    serialize
    -0.73
    POSITIVE LOGITS
    styleUrls
    0.95
     SCOT
    0.85
    }},\
    0.84
     sink
    0.83
    Convenient
    0.82
     burden
    0.81
    כול
    0.81
     Ejercicio
    0.80
     ナチュラル
    0.80
     effe
    0.80
    Activations Density 0.024%

    No Known Activations