© 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. 16-GEMMASCOPE-2-RES-262K
    7. 35899
    Prev
    Next
    INDEX
    Explanations

    rb file opening

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ה
    0.99
    u
    0.75
    on
    0.73
    z
    0.71
    IANS
    0.71
    oyeva
    0.70
    d
    0.70
    न
    0.69
    lendi
    0.68
    i
    0.68
    POSITIVE LOGITS
     innovative
    0.58
     ulike
    0.56
     irreg
    0.54
     olika
    0.53
     phosphate
    0.53
     welche
    0.52
     movable
    0.52
     integrative
    0.52
    ة
    0.51
     arbejde
    0.50
    Activations Density 0.000%

    No Known Activations