© 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. 95469
    Prev
    Next
    INDEX
    Explanations

    questions or code declarations

    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
     at
    -2.25
     and
    -2.23
     like
    -2.19
     as
    -2.09
     before
    -2.08
     when
    -2.02
     because
    -1.98
     their
    -1.96
     during
    -1.94
     all
    -1.93
    POSITIVE LOGITS
    ܆
    1.91
     prêtre
    1.80
    ᕮ
    1.77
    킁
    1.76
     corriger
    1.75
    熥
    1.75
    ౭
    1.73
    狴
    1.72
     faciliter
    1.70
     discuter
    1.68
    Activations Density 0.000%

    No Known Activations