© 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. 113429
    Prev
    Next
    INDEX
    Explanations

    tectonic, cuneiform, microtubules

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

    geological and anatomical terminology related to structural formations.

    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
    涠
    -2.42
    する
    -2.42
    lossians
    -2.39
    他们的
    -2.36
    s
    -2.31
    ی
    -2.27
    鯪
    -2.22
    焢
    -2.20
    !"
    -2.13
     luci
    -2.06
    POSITIVE LOGITS
    D
    2.09
     savvy
    2.08
    E
    2.06
    ↵
    2.00
    \
    2.00
    </sup>
    1.95
     sabias
    1.91
     碗
    1.90
     très
    1.86
     presque
    1.84
    Activations Density 0.002%

    No Known Activations