© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63797
    Prev
    Next
    INDEX
    Explanations

    cloud platform or provider

    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
     NFT
    -0.90
    Scorpion
    -0.89
    berglass
    -0.88
    cursed
    -0.86
    elancer
    -0.82
     IRL
    -0.82
     flush
    -0.81
     IMO
    -0.80
    Demografie
    -0.78
     GBA
    -0.77
    POSITIVE LOGITS
     cloud
    2.45
     Cloud
    2.14
    cloud
    2.06
    Cloud
    1.90
     clouds
    1.85
     Clouds
    1.77
    Clouds
    1.60
     CLOUD
    1.59
    CLOUD
    1.58
    clouds
    1.55
    Activations Density 0.055%

    No Known Activations