© 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. 14176
    Prev
    Next
    INDEX
    Explanations

    Purpose, requests, or states

    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
     emplois
    -1.66
    駅から
    -1.56
     médec
    -1.51
    konos
    -1.46
    ּוֹ
    -1.46
     waaronder
    -1.42
    ִּ
    -1.41
     traitements
    -1.41
     آهن
    -1.39
    Horário
    -1.38
    POSITIVE LOGITS
     сахара
    1.84
     my
    1.73
     our
    1.55
     Pfar
    1.51
    🪳
    1.50
     this
    1.41
     mesmas
    1.40
    ֺ
    1.39
    ﷲ
    1.34
    ׇ
    1.33
    Activations Density 0.235%

    No Known Activations