© 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. 68299
    Prev
    Next
    INDEX
    Explanations

    numbers following text

    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
     柱
    -0.83
    んですけど
    -0.81
     Lokales
    -0.80
     面包
    -0.77
     PSO
    -0.77
    ラックス
    -0.77
     representantes
    -0.77
     asociaciones
    -0.77
    うえ
    -0.77
     gevoel
    -0.76
    POSITIVE LOGITS
    nejšie
    0.88
    を
    0.84
     SPRINGS
    0.84
    ьем
    0.83
     Itself
    0.81
     henkilö
    0.80
     製作
    0.79
     sort
    0.79
    sort
    0.79
     新品
    0.79
    Activations Density 0.009%

    No Known Activations