© 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. 95441
    Prev
    Next
    INDEX
    Explanations

    coding, language, specific technical terms

    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
     in
    -1.64
     with
    -1.55
     at
    -1.48
     through
    -1.47
     and
    -1.47
     from
    -1.45
     during
    -1.41
     on
    -1.33
     out
    -1.32
     can
    -1.31
    POSITIVE LOGITS
    extremely
    1.52
     erhi
    1.45
    albeit
    1.45
     miniaturka
    1.41
    EVERY
    1.41
     núm
    1.40
    Believe
    1.38
     utilização
    1.37
    implemented
    1.36
    蹀
    1.32
    Activations Density 0.028%

    No Known Activations