© 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-65K
    7. 3777
    Prev
    Next
    INDEX
    Explanations

    name or title

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     comical
    0.64
     tıkl
    0.62
    <unused288>
    0.61
     unsightly
    0.60
     اﻻ
    0.57
    <unused1873>
    0.57
    𝒈
    0.57
     curls
    0.56
    𝒟
    0.55
     autocor
    0.54
    POSITIVE LOGITS
    2
    0.86
    IR
    0.78
    4
    0.77
    5
    0.71
    3
    0.70
    EM
    0.68
    ER
    0.68
    IV
    0.66
    ing
    0.65
    8
    0.65
    Activations Density 0.000%

    No Known Activations