© 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. 10617
    Prev
    Next
    INDEX
    Explanations

    list or breakdown

    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
    2
    1.23
    3
    1.20
    và
    1.20
     а
    1.19
    the
    1.15
     a
    1.11
    and
    1.11
    pe
    1.08
    1
    1.03
    ilience
    0.99
    POSITIVE LOGITS
     will
    1.23
     wording
    1.22
     criteria
    1.20
     could
    1.11
     specifications
    1.10
     should
    1.02
     criteri
    0.98
     ejempl
    0.97
     phrasing
    0.97
     is
    0.96
    Activations Density 1.803%

    No Known Activations