© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 46003
    Prev
    Next
    INDEX
    Explanations

    cyclic, abelian, rhythm, number, morphology, conjunction

    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
    ,
    0.82
     (
    0.62
    i
    0.61
     "
    0.57
     -
    0.57
    ,"
    0.55
    ;
    0.54
     data
    0.54
     R
    0.52
     G
    0.52
    POSITIVE LOGITS
     coração
    0.55
    unternehmen
    0.54
    ahanglan
    0.52
     predsjed
    0.52
    ֣
    0.50
    羢
    0.50
     सेलेना
    0.49
     entreprene
    0.49
     corazón
    0.48
    মায়
    0.48
    Activations Density 0.000%

    No Known Activations