© 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. 6410
    Prev
    Next
    INDEX
    Explanations

    of [proper noun]

    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
     delicacies
    1.17
    и
    1.17
     chocolates
    1.16
     qualities
    1.15
     pretzels
    1.13
     possessions
    1.11
     celebrations
    1.10
     groceries
    1.10
     salaries
    1.09
     estrogens
    1.09
    POSITIVE LOGITS
    t
    1.24
    n
    1.04
    is
    1.00
    c
    0.95
    4
    0.95
    1
    0.95
    <0x80>
    0.93
    asia
    0.89
    ik
    0.87
    Maximum
    0.87
    Activations Density 0.059%

    No Known Activations