© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 10771
    Prev
    Next
    INDEX
    Explanations

    `!--Two` sequence in responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     minimal
    1.21
     better
    1.01
     trivially
    0.99
     sever
    0.98
     minimum
    0.96
     hardware
    0.95
     parts
    0.94
     seed
    0.94
     Silicon
    0.93
     (
    0.93
    POSITIVE LOGITS
    img
    1.24
    html
    1.12
    Auc
    1.11
    iframe
    1.09
    ><
    1.08
    ][/
    1.08
     น้ํา
    1.07
    =”
    1.07
    ]>
    1.05
    NewLine
    1.03
    Activations Density 0.051%

    No Known Activations