© 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. 10-GEMMASCOPE-RES-131K
    7. 87335
    Prev
    Next
    INDEX
    Explanations

    introducing examples or questions

    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_10/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
    aringan
    -1.39
    3
    -1.37
     alltså
    -1.35
    ters
    -1.33
    teness
    -1.30
    ins
    -1.27
    0
    -1.27
    9
    -1.25
    你
    -1.24
     aussi
    -1.23
    POSITIVE LOGITS
     our
    1.65
     when
    1.57
     veículos
    1.37
     frecuentemente
    1.30
    umid
    1.28
    siamo
    1.27
     spesso
    1.25
    viding
    1.22
     such
    1.21
     już
    1.20
    Activations Density 0.050%

    No Known Activations