© 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. 71930
    Prev
    Next
    INDEX
    Explanations

    even though

    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
     myös
    -1.89
     also
    -1.88
     גם
    -1.86
     également
    -1.84
     również
    -1.70
     همچنین
    -1.70
    also
    -1.57
     також
    -1.57
     επίσης
    -1.52
     även
    -1.51
    POSITIVE LOGITS
     can
    2.23
     could
    1.83
     when
    1.50
     which
    1.46
     now
    1.34
     cannot
    1.27
     as
    1.27
     get
    1.24
     had
    1.22
    !
    1.20
    Activations Density 0.029%

    No Known Activations