© 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. 73450
    Prev
    Next
    INDEX
    Explanations

    Eu(3+)@SiO2, Er³⁺:KPb₂Cl₅, DA, PC61BM, P-700, 3-hexylthiophene

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

    colons in scientific notation, chemical formulas, and time formats.

    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
    and
    -2.20
    E
    -2.03
    just
    -2.02
    S
    -2.00
    $
    -1.99
    D
    -1.95
     just
    -1.95
     is
    -1.94
     when
    -1.89
    V
    -1.89
    POSITIVE LOGITS
    Exemple
    2.28
    囖
    2.25
    
    2.17
    Parce
    2.06
    嚒
    2.03
     opérateur
    2.03
    kleine
    2.02
    螃
    2.02
    ilustra
    2.00
    mbgg
    2.00
    Activations Density 0.040%

    No Known Activations