© 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. 66293
    Prev
    Next
    INDEX
    Explanations

    arrangements and availability

    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
     یعنی
    -1.48
     religieuses
    -1.38
     existant
    -1.34
     papillon
    -1.32
    作战
    -1.25
     
    -1.23
     começo
    -1.20
    「
    -1.19
    плек
    -1.19
     philippe
    -1.17
    POSITIVE LOGITS
     your
    2.30
     during
    1.82
     our
    1.65
     these
    1.55
     their
    1.47
    そのような
    1.41
     jika
    1.40
    ּוֹ
    1.39
     if
    1.38
     such
    1.37
    Activations Density 0.046%

    No Known Activations