© 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. 26279
    Prev
    Next
    INDEX
    Explanations

    action verb followed by descriptor

    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
     Cæsar
    -1.16
    фы
    -1.06
     reduce
    -1.06
    IELD
    -1.05
     Both
    -1.05
     检测
    -1.04
     ensure
    -1.03
    Both
    -1.02
    It
    -1.01
    $};
    -1.00
    POSITIVE LOGITS
     and
    1.32
    beautiful
    1.20
     إد
    1.18
     Спи
    1.10
     ſont
    1.10
     the
    1.09
     kolik
    1.08
     hırka
    1.02
     veulent
    1.00
     zapato
    1.00
    Activations Density 0.091%

    No Known Activations