© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 195322
    Prev
    Next
    INDEX
    Explanations

    list components

    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_40_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
     kammam
    0.38
     футболдук
    0.37
    циях
    0.37
     interacción
    0.37
     ګ
    0.37
     Throughout
    0.36
    interaction
    0.36
     आहोत
    0.36
    力
    0.36
     interação
    0.36
    POSITIVE LOGITS
    Transparent
    0.44
    Trust
    0.44
     Total
    0.41
     Trust
    0.41
    ldre
    0.41
    Image
    0.40
    Total
    0.40
     rave
    0.40
    Land
    0.40
    Conservation
    0.40
    Activations Density 0.002%

    No Known Activations