© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38891
    Prev
    Next
    INDEX
    Explanations

    topics and definitions

    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
     religieux
    -1.41
     cukru
    -1.35
     иллюстрация
    -1.34
     OGSÅ
    -1.34
     kokos
    -1.30
     garantir
    -1.22
    bagian
    -1.21
     teolog
    -1.20
     susc
    -1.19
     choisi
    -1.16
    POSITIVE LOGITS
    ּוֹ
    1.32
     in
    1.32
     помещении
    1.24
     respondents
    1.23
     штра
    1.17
    ַּ
    1.17
     provide
    1.16
    Ź
    1.16
     at
    1.15
     last
    1.15
    Activations Density 0.004%

    No Known Activations