© 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. 104617
    Prev
    Next
    INDEX
    Explanations

    abbreviations or identifiers

    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
    \
    -2.67
    In
    -2.45
    Because
    -2.06
     Because
    -2.06
     glorious
    -2.06
     illustrious
    -2.06
    ).
    -2.06
    地说道
    -2.03
     time
    -2.02
     Fazit
    -2.02
    POSITIVE LOGITS
     pembun
    2.28
    to
    2.14
    缯
    2.06
     mè
    2.03
    and
    2.02
    něž
    1.91
     peuvent
    1.89
    縞
    1.88
    女孩子
    1.84
     chè
    1.84
    Activations Density 0.019%

    No Known Activations