© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59111
    Prev
    Next
    INDEX
    Explanations

    expressing confusion about how or why

    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
     when
    -2.08
     Probably
    -1.58
    When
    -1.54
     These
    -1.52
     cerdas
    -1.50
     probably
    -1.45
     Because
    -1.44
     ratusan
    -1.42
    Transkrypt
    -1.42
     only
    -1.41
    POSITIVE LOGITS
    up
    1.59
    f
    1.49
    ro
    1.49
    4
    1.48
    1
    1.38
     they
    1.38
    慣れて
    1.37
    ver
    1.34
    5
    1.33
    6
    1.33
    Activations Density 0.039%

    No Known Activations