© 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. 10-GEMMASCOPE-RES-131K
    7. 10883
    Prev
    Next
    INDEX
    Explanations

    asking or wondering about something

    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_10/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
    '
    -1.63
    They
    -1.56
    輒
    -1.46
     They
    -1.38
     لهذه
    -1.33
    ectady
    -1.32
     übernahm
    -1.32
     этом
    -1.28
     этих
    -1.27
    鱨
    -1.27
    POSITIVE LOGITS
    Kuva
    1.56
     your
    1.56
    Ivoire
    1.51
     pö
    1.45
     работать
    1.45
     verdura
    1.44
    Продам
    1.41
    zić
    1.41
     susun
    1.41
    鬣
    1.40
    Activations Density 0.001%

    No Known Activations