© 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. 6716
    Prev
    Next
    INDEX
    Explanations

    source or origin

    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
    on
    0.71
    p
    0.71
    ן
    0.68
     on
    0.68
     xhrObj
    0.63
    E
    0.62
    D
    0.62
    in
    0.61
    ozyg
    0.59
     fervor
    0.59
    POSITIVE LOGITS
     whence
    0.91
     thence
    0.86
     afar
    0.82
     څخه
    0.79
     standpoint
    0.73
     ጋር
    0.70
    сюда
    0.66
     सटे
    0.66
    م
    0.64
    ม
    0.64
    Activations Density 0.137%

    No Known Activations