© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 9438
    Prev
    Next
    INDEX
    Explanations

    alternatives or questions

    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
    FailureListener
    -1.25
    ཫ
    -1.17
    archiwizowane
    -1.16
    𖤍
    -1.13
    enemy
    -1.12
    success
    -1.08
    νώ
    -1.06
     PUSTAKA
    -1.06
     OPINION
    -1.06
     alue
    -1.06
    POSITIVE LOGITS
    ?
    1.95
    それとも
    1.75
    还是
    1.48
    還是
    1.41
     still
    1.35
    あくまで
    1.33
     merely
    1.25
     just
    1.21
     רק
    1.16
     more
    1.13
    Activations Density 0.029%

    No Known Activations