© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 36436
    Prev
    Next
    INDEX
    Explanations

    most important part

    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
     hvorfor
    -1.23
     útiles
    -1.20
     frecuente
    -1.18
     überrascht
    -1.17
     exportaciones
    -1.17
     svårt
    -1.15
     sikkert
    -1.15
    様々
    -1.14
    してました
    -1.14
     únicamente
    -1.12
    POSITIVE LOGITS
     of
    4.38
     peines
    1.63
    ของ
    1.59
     sosi
    1.59
     guerres
    1.41
     aimé
    1.40
     rigue
    1.39
     défauts
    1.38
     visuel
    1.38
     brille
    1.37
    Activations Density 0.033%

    No Known Activations