© 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. 34-GEMMASCOPE-RES-131K
    7. 25962
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    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
     explicado
    -1.37
     on
    -1.32
     in
    -1.27
     and
    -1.22
     or
    -1.14
    書の
    -1.14
     seemed
    -1.13
     cleverly
    -1.11
    鞏
    -1.09
     came
    -1.08
    POSITIVE LOGITS
    both
    1.41
    many
    1.28
    various
    1.27
     criou
    1.24
     interrom
    1.19
     .......
    1.17
    several
    1.17
    three
    1.15
    two
    1.14
     鸡蛋
    1.14
    Activations Density 0.271%

    No Known Activations