© 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. 13566
    Prev
    Next
    INDEX
    Explanations

    induction and therapy

    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
    cartier
    -1.10
     mógł
    -1.09
    /*!
    -0.97
     tikai
    -0.95
     pourriez
    -0.94
    っていない
    -0.94
     принадлежа
    -0.93
    ෆ
    -0.93
    [{{
    -0.92
     dennoch
    -0.91
    POSITIVE LOGITS
     trasforma
    1.16
    Shal
    1.07
    另一种
    1.03
     pagare
    0.99
    Reak
    0.98
    Več
    0.97
    Paket
    0.96
    是这样的
    0.96
    Shr
    0.95
    Monter
    0.95
    Activations Density 0.046%

    No Known Activations