© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 44011
    Prev
    Next
    INDEX
    Explanations

    levodopa, shared computing, cohesive forces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    0.45
    rokken
    0.42
    <0x9C>
    0.41
    葬
    0.40
    prés
    0.39
    نى
    0.39
    acji
    0.39
    Een
    0.38
     on
    0.38
    Ϲ
    0.38
    POSITIVE LOGITS
     continual
    0.49
     deaminase
    0.49
     serotonin
    0.46
     repl
    0.45
     critica
    0.45
     plantilla
    0.44
     sincron
    0.44
     parada
    0.43
     بیت
    0.43
     comienza
    0.42
    Activations Density 0.003%

    No Known Activations