© 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. 40766
    Prev
    Next
    INDEX
    Explanations

    far from

    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
    य
    0.70
    У
    0.69
    la
    0.63
    态
    0.63
    િંગ
    0.59
     క్ర
    0.59
    తంగా
    0.59
    حياته
    0.59
    H
    0.57
    ي
    0.57
    POSITIVE LOGITS
    遠
    0.88
     jauh
    0.83
     are
    0.71
     afield
    0.70
     furthest
    0.70
    远
    0.68
     remot
    0.67
    远的
    0.67
     remotely
    0.66
     daleko
    0.64
    Activations Density 0.072%

    No Known Activations