© 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. 26106
    Prev
    Next
    INDEX
    Explanations

    baseline or control states

    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
     aproape
    -1.08
     unbelievably
    -1.07
     revamped
    -1.04
    盘点
    -1.03
    wegg
    -1.02
     スニーカー
    -1.01
    可以说是
    -0.99
    ब्द
    -0.98
     remarkably
    -0.97
    小结
    -0.96
    POSITIVE LOGITS
     without
    1.36
     before
    1.34
     baseline
    1.33
     oryginal
    1.15
     Before
    1.12
     originale
    1.12
    baseline
    1.09
     condition
    1.08
     standard
    1.06
     Without
    1.05
    Activations Density 0.087%

    No Known Activations