© 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. 63912
    Prev
    Next
    INDEX
    Explanations

    funding programs and initiatives

    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
    cambi
    -0.95
    scl
    -0.93
    线下
    -0.79
    Unlimited
    -0.79
     Sicherheits
    -0.78
     SCL
    -0.78
     wöch
    -0.76
    andaag
    -0.76
     Burns
    -0.75
    yaretçi
    -0.74
    POSITIVE LOGITS
     aid
    1.38
     program
    1.29
     scheme
    1.22
     assistance
    1.21
     programas
    1.20
     Program
    1.19
     measures
    1.18
     programmes
    1.17
     programme
    1.17
     grant
    1.16
    Activations Density 0.012%

    No Known Activations