© 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. 48127
    Prev
    Next
    INDEX
    Explanations

    names followed by disambiguating parentheses

    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
     there
    -1.21
     but
    -1.06
     at
    -1.04
     it
    -1.03
     one
    -0.98
     still
    -0.98
     each
    -0.96
     both
    -0.96
    manchester
    -0.94
     now
    -0.88
    POSITIVE LOGITS
    <b>
    1.84
    Coordinates
    1.09
    ＂
    1.08
     '''
    1.05
    һ
    0.96
     nimmer
    0.94
    |-
    0.93
    chende
    0.93
    точки
    0.93
     Koordin
    0.92
    Activations Density 0.091%

    No Known Activations