© 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. 25917
    Prev
    Next
    INDEX
    Explanations

    boost.org/LICENSE

    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
    cyjnych
    -0.80
    JspWriter
    -0.69
     addTo
    -0.69
     phonon
    -0.67
    onBackPressed
    -0.67
     Lair
    -0.67
    enka
    -0.67
    
    -0.67
     Fiona
    -0.67
     magistrates
    -0.66
    POSITIVE LOGITS
    nissan
    0.71
     sustainability
    0.66
     SUSTAIN
    0.66
    fputs
    0.65
     guter
    0.65
    leri
    0.64
     обеспечи
    0.64
    leaders
    0.64
    ustra
    0.61
    imath
    0.61
    Activations Density 0.066%

    No Known Activations