© 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. 10054
    Prev
    Next
    INDEX
    Explanations

    by + context

    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
    م
    0.72
    m
    0.69
    м
    0.69
    म
    0.64
    ل
    0.64
    ר
    0.63
    K
    0.60
     the
    0.57
    ت
    0.57
    qui
    0.57
    POSITIVE LOGITS
    서는
    0.67
     virtue
    0.65
    cina
    0.65
     dint
    0.62
    cara
    0.60
    чена
    0.59
     deň
    0.57
    zantine
    0.57
    々に
    0.55
    cena
    0.55
    Activations Density 0.080%

    No Known Activations