© 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. 41144
    Prev
    Next
    INDEX
    Explanations

    boolean values or functions

    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
     Its
    -1.46
     tuviera
    -1.37
     krä
    -1.34
    惚
    -1.34
     querr
    -1.28
     apareció
    -1.25
     handen
    -1.23
     estuviera
    -1.23
     tuvimos
    -1.22
    -1.22
    POSITIVE LOGITS
     some
    1.81
     contextLoads
    1.55
     Anſ
    1.53
     by
    1.45
     those
    1.41
     about
    1.41
     when
    1.40
     ibi
    1.38
    ↵↵
    1.38
     photolibrary
    1.37
    Activations Density 0.020%

    No Known Activations