© 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. 11089
    Prev
    Next
    INDEX
    Explanations

    numbers and abbreviations

    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
    נְ
    -1.00
    SequentialGroup
    -0.94
    گاه
    -0.86
    ᾰ
    -0.85
    לְ
    -0.82
    pahan
    -0.81
     (_.
    -0.78
    RELEASE
    -0.78
    ties
    -0.77
    เก็บ
    -0.77
    POSITIVE LOGITS
     licenci
    0.84
     firft
    0.83
    当て
    0.81
     FÜR
    0.80
     faço
    0.79
     getChild
    0.77
    eeper
    0.75
    礼
    0.75
     isFirst
    0.75
    Contd
    0.75
    Activations Density 0.046%

    No Known Activations