© 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. 34-GEMMASCOPE-RES-131K
    7. 109478
    Prev
    Next
    INDEX
    Explanations

    conjunctive lists

    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_34/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
     этой
    -1.90
     tohoto
    -1.84
     kabát
    -1.76
    grima
    -1.75
     SUCH
    -1.68
     WHILE
    -1.67
    »).
    -1.66
    และ
    -1.66
     évo
    -1.60
     této
    -1.59
    POSITIVE LOGITS
     even
    2.81
     so
    2.52
     other
    2.48
     lastly
    2.02
     —
    1.99
     finally
    1.99
     any
    1.91
    —
    1.91
     when
    1.88
     schließlich
    1.81
    Activations Density 0.143%

    No Known Activations