© 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. 65924
    Prev
    Next
    INDEX
    Explanations

    text elements and specific entities

    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
    raciones
    -0.80
    )}+
    -0.79
    iliger
    -0.79
    mmung
    -0.76
    ABE
    -0.73
    มิ
    -0.73
    让他们
    -0.71
    Ꮤ
    -0.71
    ərbaycan
    -0.71
     gelatin
    -0.71
    POSITIVE LOGITS
     readout
    1.07
    cerita
    0.77
    pret
    0.76
    compress
    0.73
     TELL
    0.73
    列車
    0.73
     Crate
    0.73
    crate
    0.71
    光芒
    0.71
    上位
    0.70
    Activations Density 0.017%

    No Known Activations