© 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. 13925
    Prev
    Next
    INDEX
    Explanations

    action initiating or changing state

    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
     from
    -2.08
     by
    -1.46
     so
    -1.41
     very
    -1.38
     like
    -1.36
    笑意
    -1.33
     even
    -1.22
    ﻷ
    -1.22
     this
    -1.20
     everything
    -1.18
    POSITIVE LOGITS
     luminos
    1.54
    fören
    1.48
    Indien
    1.46
    vaders
    1.44
     campeonato
    1.43
     multicolore
    1.43
     relâche
    1.42
     résine
    1.38
    ಅ
    1.36
    ṇa
    1.35
    Activations Density 0.000%

    No Known Activations