© 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. 23875
    Prev
    Next
    INDEX
    Explanations

    segmentation of 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_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
    chwyd
    -0.81
    ubre
    -0.74
    PONENT
    -0.74
    Asts
    -0.74
    frontmatter
    -0.74
    aknya
    -0.73
    olz
    -0.73
    成分
    -0.72
    uji
    -0.71
    傾向
    -0.71
    POSITIVE LOGITS
     segment
    1.13
    segment
    1.13
     Segment
    1.10
    Segment
    1.02
     segments
    0.90
    segments
    0.87
     segmentos
    0.83
     segmento
    0.79
     Segments
    0.75
    Segments
    0.72
    Activations Density 0.029%

    No Known Activations