© 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. 36263
    Prev
    Next
    INDEX
    Explanations

    surnames of authors

    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
    ಝ
    -1.20
     which
    -1.16
    Nossa
    -1.13
    >("
    -1.10
    Nós
    -1.07
     caballeros
    -1.06
     entrambi
    -1.06
     accogli
    -1.05
     caballero
    -1.05
    <>();
    
    -1.05
    POSITIVE LOGITS
     junto
    1.06
     et
    1.05
     and
    1.04
     altres
    1.02
     aquesta
    1.01
    折磨
    0.98
    <sup>
    0.94
     postdoctoral
    0.91
     spf
    0.90
     erlebt
    0.89
    Activations Density 0.076%

    No Known Activations