© 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. 35231
    Prev
    Next
    INDEX
    Explanations

    completion or occurrence

    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
     of
    -2.03
     diſt
    -1.28
    ఽ
    -1.18
     incredi
    -1.14
    很多的
    -1.13
     molte
    -1.13
     molti
    -1.13
    potentially
    -1.11
     Collagen
    -1.11
     molto
    -1.11
    POSITIVE LOGITS
     sintió
    1.27
     their
    1.27
     Among
    1.17
     its
    1.14
     Those
    1.13
     One
    1.12
     Eight
    1.12
     Basically
    1.09
     it
    1.09
     verwijzen
    1.09
    Activations Density 0.057%

    No Known Activations