© 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. 22-GEMMASCOPE-RES-131K
    7. 72259
    Prev
    Next
    INDEX
    Explanations

    alternative or additional

    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_22/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
    抡
    -1.02
     étan
    -0.95
     télécommande
    -0.91
     châssis
    -0.91
     thậm
    -0.84
     ECONOMIC
    -0.84
     行っ
    -0.82
    Dab
    -0.82
     éta
    -0.81
    jsko
    -0.81
    POSITIVE LOGITS
     because
    1.24
     vision
    0.96
     secondly
    0.90
     also
    0.89
     puisqu
    0.88
     **
    0.84
    SIGNATURE
    0.84
     criminal
    0.82
     puisque
    0.81
     Grow
    0.81
    Activations Density 0.093%

    No Known Activations