© 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. 33792
    Prev
    Next
    INDEX
    Explanations

    xhtml doctype

    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
     atque
    -0.83
     molé
    -0.73
     come
    -0.72
    Schon
    -0.72
     všechny
    -0.69
    Come
    -0.69
     explicar
    -0.69
     bière
    -0.69
     cmd
    -0.68
    OMC
    -0.68
    POSITIVE LOGITS
     dandruff
    0.69
    CRUD
    0.68
    zow
    0.66
     radon
    0.65
    òa
    0.65
    Ubic
    0.64
     gro
    0.64
     Puff
    0.64
    eni
    0.64
    ことに
    0.64
    Activations Density 0.064%

    No Known Activations