© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 2023
    Prev
    Next
    INDEX
    Explanations

    digits followed by addition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-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
    DBG
    1.69
    󠁣
    1.61
    dB
    1.57
     Aussch
    1.54
     exportation
    1.53
    <unused2056>
    1.52
     SPEC
    1.51
     export
    1.50
    <unused437>
    1.48
    HJ
    1.48
    POSITIVE LOGITS
    1.31
    ↵↵
    1.12
     online
    1.07
    online
    1.07
    ↵
    1.06
     Online
    1.05
    1
    1.05
     Internet
    1.03
    Online
    0.97
     il
    0.96
    Activations Density 0.045%

    No Known Activations