© 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. 22-GEMMASCOPE-RES-131K
    7. 128409
    Prev
    Next
    INDEX
    Explanations

    file operations and paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    <bos>
    -1.41
    lor
    -1.20
    ombies
    -1.14
    lossians
    -1.13
     många
    -1.09
     HAPPENED
    -1.09
    AGGIO
    -1.08
    jsonwebtoken
    -1.05
    ars
    -1.04
    mics
    -1.04
    POSITIVE LOGITS
     کردیم
    1.20
    死ぬ
    1.17
    應該
    1.15
     nearby
    1.13
    ﹙
    1.08
    宜蘭
    1.05
     prosím
    1.05
    ‪.‬‬
    1.05
     خواهیم
    1.03
     Puts
    1.03
    Activations Density 0.010%

    No Known Activations