© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58208
    Prev
    Next
    INDEX
    Explanations

    Promise resolution

    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
    guia
    -0.96
     рав
    -0.79
    πάρχ
    -0.74
     ব্য
    -0.73
     range
    -0.72
    aute
    -0.71
    guía
    -0.71
    だが
    -0.71
    валась
    -0.71
     value
    -0.71
    POSITIVE LOGITS
     resolutions
    1.33
    resolve
    1.33
    resolution
    1.29
     resolution
    1.29
     résolution
    1.27
     resolve
    1.19
    Resolution
    1.16
     resolves
    1.10
     resolución
    1.04
     resolução
    1.02
    Activations Density 0.005%

    No Known Activations