© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 34493
    Prev
    Next
    INDEX
    Explanations

    best of both worlds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     husbandry
    1.02
    ﻁ
    1.01
     Dubna
    0.99
    ﺘ
    0.98
     druž
    0.98
     tbh
    0.96
    ﻤ
    0.95
    脖
    0.95
     Hartree
    0.95
    ﻄ
    0.93
    POSITIVE LOGITS
    ের
    0.89
    ुल
    0.87
     deux
    0.81
     Deux
    0.74
    enche
    0.73
    ano
    0.70
    ों
    0.68
    xD
    0.68
     ومن
    0.67
    JA
    0.67
    Activations Density 0.000%

    No Known Activations