© 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. 4781
    Prev
    Next
    INDEX
    Explanations

    explaining "equivalent"

    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
    ил
    0.96
    ες
    0.90
     କ
    0.89
    </h3>
    0.89
     مُ
    0.88
    ING
    0.87
     ታ
    0.87
    お金
    0.84
    ة
    0.83
     crucified
    0.83
    POSITIVE LOGITS
     equivalent
    1.30
     Equivalent
    1.08
    0
    1.05
     equivalente
    1.03
     equivalents
    1.02
    x
    0.98
    ah
    0.92
    on
    0.89
    )
    0.85
    Equivalent
    0.83
    Activations Density 0.021%

    No Known Activations