© 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. 65758
    Prev
    Next
    INDEX
    Explanations

    numbers following specific characters

    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
     musées
    -1.41
     chré
    -1.33
     libération
    -1.15
    Ǧ
    -1.07
     решил
    -1.07
     устройств
    -1.06
     poussière
    -1.06
     яйцо
    -1.03
     žal
    -1.02
    bình
    -1.00
    POSITIVE LOGITS
     кроссовки
    1.16
     process
    1.16
    hline
    1.13
    ᾽
    1.13
    шні
    1.10
    ֶּ
    1.10
     скриншот
    1.09
     Functional
    1.09
    process
    1.09
     processo
    1.06
    Activations Density 0.093%

    No Known Activations