© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93146
    Prev
    Next
    INDEX
    Explanations

    import statements and code definitions

    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
     pomen
    -1.07
    Stav
    -1.01
     without
    -1.01
    Toto
    -0.98
     in
    -0.97
    ohne
    -0.96
     сок
    -0.95
     scenario
    -0.95
    Profes
    -0.94
     навіть
    -0.94
    POSITIVE LOGITS
    ające
    1.08
     hà
    1.06
    naires
    1.06
    ׳
    1.05
     impromptu
    1.05
    zaak
    1.05
    see
    1.02
    ;"
    1.01
    ʼ
    1.01
    tape
    1.00
    Activations Density 0.003%

    No Known Activations