© 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. 39451
    Prev
    Next
    INDEX
    Explanations

    HTML tags and code separators leading to content

    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
     its
    -1.14
     Tieren
    -1.09
    Error
    -1.04
    }
    -1.03
     some
    -1.02
    šanās
    -1.00
    !（
    -1.00
     mencapai
    -0.98
    ！(
    -0.98
     máscaras
    -0.98
    POSITIVE LOGITS
    还有一
    1.26
    那时候
    1.25
    可以说是
    1.25
    Acerca
    1.08
    悫
    1.06
     /\
    1.05
    可谓
    1.05
    Mmm
    1.04
    Popis
    1.02
    archiviato
    1.02
    Activations Density 0.000%

    No Known Activations