© 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. 15367
    Prev
    Next
    INDEX
    Explanations

    admission a

    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
    }$
    -1.04
     miesięcy
    -1.03
     at
    -0.93
    ധ
    -0.93
    You
    -0.93
     some
    -0.92
     an
    -0.90
    !")
    -0.90
    >';
    -0.89
     skóry
    -0.89
    POSITIVE LOGITS
    竟然是
    1.11
     teď
    1.06
     regeringen
    1.05
    材質
    1.03
     fielder
    1.01
     detenidos
    1.00
    aneity
    1.00
     weißem
    1.00
     ordf
    0.99
     katk
    0.99
    Activations Density 0.058%

    No Known Activations