© 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-16K
    7. 11676
    Prev
    Next
    INDEX
    Explanations

    byte string encoding

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ↵↵
    1.12
    3
    1.11
    4
    1.09
    V
    1.04
    \|_{
    1.00
    I
    0.99
    6
    0.98
    0.98
    M
    0.96
    0.96
    POSITIVE LOGITS
    イナー
    1.08
     trabalh
    1.01
     abordagem
    0.96
     TRANSP
    0.94
     contrôler
    0.92
     quoi
    0.91
     resolver
    0.89
     améliorer
    0.89
     grader
    0.89
     pretext
    0.88
    Activations Density 0.523%

    No Known Activations