© 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. 60736
    Prev
    Next
    INDEX
    Explanations

    legal documents and news citations

    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
    replica
    -0.81
    vspace
    -0.79
     circonst
    -0.78
     rodzaju
    -0.76
    municip
    -0.75
     Ola
    -0.75
     chêne
    -0.74
    Miner
    -0.73
    \@
    -0.73
    Ola
    -0.73
    POSITIVE LOGITS
    iers
    0.79
     MO
    0.74
     efficient
    0.72
     साथ
    0.72
    mtp
    0.71
     na
    0.71
     Bc
    0.70
     pure
    0.69
    蜘蛛
    0.69
    MO
    0.69
    Activations Density 0.003%

    No Known Activations