© 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. 26056
    Prev
    Next
    INDEX
    Explanations

    MMA Junkie

    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
     acte
    -1.05
     repens
    -0.99
     chirurgie
    -0.98
     élimin
    -0.97
     amerik
    -0.97
     protes
    -0.97
     lanterna
    -0.96
    蚰
    -0.95
     quarto
    -0.94
     officier
    -0.94
    POSITIVE LOGITS
     then
    1.15
    9
    1.02
     Ctrl
    0.89
    哩
    0.86
     findings
    0.85
    тності
    0.84
    冽
    0.81
     also
    0.80
     القص
    0.79
     it
    0.79
    Activations Density 0.007%

    No Known Activations