© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84492
    Prev
    Next
    INDEX
    Explanations

    comments, replies, and posts

    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_34/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
    ḥ
    -0.82
    Ṭ
    -0.81
     summer
    -0.80
    więks
    -0.79
    Ṣ
    -0.79
    вери
    -0.78
    slidesToShow
    -0.77
     extensive
    -0.77
     Waters
    -0.76
    광
    -0.75
    POSITIVE LOGITS
    DATASET
    0.96
     nível
    0.88
    Permalink
    0.83
     生産
    0.83
     ず
    0.82
     reply
    0.82
     $+\
    0.81
     Helpful
    0.81
     aprendizagem
    0.81
    のように
    0.78
    Activations Density 0.014%

    No Known Activations