© 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. 36034
    Prev
    Next
    INDEX
    Explanations

    database table names and 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
    を
    -2.09
    <bos>
    -2.08
    そして
    -1.95
    や
    -1.91
    が
    -1.82
    と
    -1.79
    がありますが
    -1.74
    は
    -1.65
    も
    -1.64
    で
    -1.56
    POSITIVE LOGITS
    際には
    1.81
    場合には
    1.77
    んですよね
    1.73
    つづく
    1.66
    で見る
    1.65
     their
    1.64
    ところに
    1.55
     such
    1.52
    為に
    1.51
    んですね
    1.48
    Activations Density 0.062%

    No Known Activations