© 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. 61003
    Prev
    Next
    INDEX
    Explanations

    formulas for storytelling

    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
     আলোচনার
    0.55
     discusses
    0.49
     vervolgens
    0.49
    Е
    0.47
     explains
    0.46
     fanden
    0.45
    苅
    0.45
    יו
    0.44
     lingers
    0.44
     deterior
    0.44
    POSITIVE LOGITS
     cortes
    0.45
    insured
    0.45
     inning
    0.39
     Ashanti
    0.39
    nemouth
    0.39
    np
    0.39
     জানা
    0.38
    ]")
    0.38
     än
    0.38
    सूचित
    0.38
    Activations Density 0.010%

    No Known Activations