© 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. 31-GEMMASCOPE-2-RES-65K
    7. 10706
    Prev
    Next
    INDEX
    Explanations

    open weights and command

    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_65k_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
     is
    0.84
     a
    0.75
    0.68
     \
    0.58
     on
    0.58
     it
    0.56
     (
    0.48
    ")
    0.47
     Pada
    0.47
    oda
    0.46
    POSITIVE LOGITS
    ле
    0.64
    ча
    0.62
    га
    0.61
    ко
    0.59
    ن
    0.58
    ли
    0.56
    น
    0.55
     for
    0.54
     смысле
    0.51
    पिक्सल
    0.51
    Activations Density 0.102%

    No Known Activations