© 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. 38650
    Prev
    Next
    INDEX
    Explanations

    even introducing exception

    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
     and
    -1.91
     también
    -1.59
     וכן
    -1.54
     także
    -1.41
     myös
    -1.41
     également
    -1.38
    fordshire
    -1.35
     também
    -1.33
    ificato
    -1.30
     również
    -1.28
    POSITIVE LOGITS
    ,
    1.55
     though
    1.55
    olkata
    1.38
     bowiem
    1.24
    '
    1.23
    それでは
    1.21
     the
    1.18
    ～～～
    1.13
    though
    1.12
    呦
    1.09
    Activations Density 0.012%

    No Known Activations