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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11515
    Prev
    Next
    INDEX
    Explanations

    lengthy documentation, safety equipment, comprehensive GIS

    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
     those
    -1.43
     not
    -1.20
     after
    -1.19
     with
    -1.17
     ominous
    -1.14
     It
    -1.14
    いわゆる
    -1.13
     (
    -1.12
     eight
    -1.12
     six
    -1.10
    POSITIVE LOGITS
     persil
    1.28
     kanker
    1.27
     gouttes
    1.22
     basili
    1.16
     kapital
    1.15
     geene
    1.13
    gemaakt
    1.13
     Ajouter
    1.13
     maniere
    1.13
     frança
    1.12
    Activations Density 0.117%

    No Known Activations