© 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. 27284
    Prev
    Next
    INDEX
    Explanations

    Oh, 1, st

    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
     что
    -1.24
     anything
    -1.12
     terdekat
    -1.08
     on
    -1.07
     people
    -1.04
     spesies
    -1.03
     episodio
    -1.02
     industria
    -1.00
     Ikke
    -1.00
     not
    -0.99
    POSITIVE LOGITS
    1.34
    Comté
    1.21
    rofl
    1.03
     lorsque
    1.02
     intrigu
    1.02
    ınıza
    1.00
    дыду
    0.98
    iTunes
    0.98
    ;

    0.97
    гка
    0.97
    Activations Density 0.008%
    No Known Activations