© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14307
    Prev
    Next
    INDEX
    Explanations

    common sayings and proverbs

    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
     like
    -1.23
    without
    -1.07
     unlike
    -0.96
    (['/
    -0.94
    using
    -0.91
     upon
    -0.91
     They
    -0.90
     ‘
    -0.88
     NEW
    -0.86
    atterns
    -0.85
    POSITIVE LOGITS
    这句话
    1.18
    諺
    1.15
     případ
    1.10
    teness
    1.02
    Frage
    1.00
     any
    0.99
     gedurende
    0.99
    ÁR
    0.99
    jarse
    0.98
    Zitat
    0.98
    Activations Density 0.028%

    No Known Activations