© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 49960
    Prev
    Next
    INDEX
    Explanations

    what is or what kind of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     duż
    0.45
     શહે
    0.45
    Ș
    0.44
    銇
    0.44
    reqParam
    0.43
    きた
    0.43
    Bootstrap
    0.43
    す
    0.43
    л
    0.43
     oferta
    0.42
    POSITIVE LOGITS
    ER
    0.39
    <0x0D>
    0.37
     enmity
    0.36
     swelling
    0.35
    2
    0.35
     humiliation
    0.35
    .
    0.35
    (
    0.35
     stiffness
    0.34
    ong
    0.34
    Activations Density 0.021%

    No Known Activations