© 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. 71618
    Prev
    Next
    INDEX
    Explanations

    code references and headings

    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
     p
    -1.35
     l
    -1.33
     N
    -1.15
     m
    -1.09
     other
    -1.08
     T
    -1.08
     Un
    -1.08
     v
    -1.05
     $
    -1.05
     some
    -1.05
    POSITIVE LOGITS
     portavoz
    1.26
     diseñadores
    1.26
    を変更
    1.26
    щению
    1.20
    țiile
    1.20
    mặt
    1.19
     къде
    1.19
     gestionar
    1.16
     diseñar
    1.15
    konferenz
    1.15
    Activations Density 0.003%

    No Known Activations