© 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. 12746
    Prev
    Next
    INDEX
    Explanations

    Asian outdoor

    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
     over
    -1.22
     numerous
    -1.20
     various
    -1.19
     large
    -1.15
     huge
    -1.08
     increased
    -1.06
     on
    -1.05
     unusually
    -1.05
     extensive
    -1.05
     very
    -1.03
    POSITIVE LOGITS
     クリニック
    1.20
     accompagner
    1.17
     disponibilités
    1.11
     '*
    1.08
    MY
    1.08
    และ
    1.05
     déplacer
    1.05
    вою
    1.04
    ;,
    1.04
     and
    1.04
    Activations Density 0.009%

    No Known Activations