© 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. 34-GEMMASCOPE-RES-131K
    4. 82395
    Prev
    Next
    INDEX
    Explanations

    GNU General Public 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
    Drums
    -0.82
     as
    -0.82
     happier
    -0.80
     UserId
    -0.77
    Dama
    -0.73
     wheelchair
    -0.72
    engkapnya
    -0.71
    riol
    -0.70
     arguably
    -0.70
     HAZARD
    -0.70
    POSITIVE LOGITS
    
    0.86
    rew
    0.81
    fits
    0.81
    mv
    0.79
     nears
    0.78
     Dole
    0.77
    GEBURTSDATUM
    0.77
    整体
    0.77
    rtner
    0.76
    }.
    0.76
    Activations Density 0.135%

    No Known Activations