© 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. 11660
    Prev
    Next
    INDEX
    Explanations

    hindrance, impede, prevent, block

    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
     Ее
    1.03
    ’
    0.96
     iż
    0.96
    `
    0.93
    ut
    0.89
    <tr>
    0.87
    Date
    0.87
     Bu
    0.87
    0.87
     BOM
    0.86
    POSITIVE LOGITS
    ка
    1.41
    ية
    1.39
    ів
    1.25
    তম
    1.23
    ם
    1.20
    ません
    1.18
    ર
    1.18
    кое
    1.15
    きます
    1.15
    íí
    1.15
    Activations Density 0.129%

    No Known Activations