© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 56727
    Prev
    Next
    INDEX
    Explanations

    dependency relations

    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
    Negative Logits
     street
    0.56
     parlato
    0.49
    街
    0.48
     gyven
    0.47
     cidad
    0.45
     toman
    0.43
     gioco
    0.41
     remboursement
    0.41
     horsepower
    0.41
     ulic
    0.41
    POSITIVE LOGITS
    assignments
    0.44
     এরপর
    0.43
    Ṛ
    0.40
    Ǎ
    0.40
    ibs
    0.39
     उन्हें
    0.39
    ări
    0.39
     Саме
    0.38
    Electronics
    0.38
    stellungen
    0.38
    Activations Density 0.014%

    No Known Activations