© 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. 66166
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure

    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
     veden
    -1.01
     trzech
    -0.95
    一邊
    -0.95
    全体的に
    -0.92
     הַ
    -0.92
     Motors
    -0.91
     kolik
    -0.90
    女性の
    -0.85
    やっぱ
    -0.83
    muñeca
    -0.83
    POSITIVE LOGITS
     will
    1.15
     may
    0.96
     or
    0.93
    struts
    0.84
     agi
    0.82
    🡪
    0.81
    可能
    0.81
    toxicity
    0.81
     креди
    0.81
     pera
    0.81
    Activations Density 0.005%

    No Known Activations