© 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. 84779
    Prev
    Next
    INDEX
    Explanations

    metal oxides and semiconductor materials

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

    chemical compounds, elements, and materials in scientific literature about catalysts and nanomaterials.

    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
    aned
    -1.45
    ebly
    -1.45
    ternut
    -1.42
    ’
    -1.35
    ﹝
    -1.34
     décidé
    -1.32
     usein
    -1.30
    𝟏
    -1.30
    igth
    -1.27
    generating
    -1.25
    POSITIVE LOGITS
     of
    1.32
     —
    1.05
     темати
    1.03
    フリー
    1.02
    Sind
    1.00
     Phones
    0.97
    cá
    0.97
     Cens
    0.97
    ristiana
    0.97
    hias
    0.96
    Activations Density 0.179%

    No Known Activations