© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13561
    Prev
    Next
    INDEX
    Explanations

    start of sentence tokens

    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
    dames
    -1.30
     mentales
    -1.11
     mengumumkan
    -1.10
    única
    -1.09
    的气息
    -1.08
     kılı
    -1.08
     blusa
    -1.08
     яйцо
    -1.07
     Encyclopædia
    -1.07
    дѣ
    -1.07
    POSITIVE LOGITS
    :"-
    1.41
     you
    1.41
     your
    1.41
    🩱
    1.36
     would
    1.32
    baomidou
    1.31
     unfortunately
    1.27
    :"#
    1.24
     here
    1.23
    ֶּ
    1.18
    Activations Density 0.004%

    No Known Activations