© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83730
    Prev
    Next
    INDEX
    Explanations

    orphan or orphaned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    鞮
    -2.28
    䛗
    -2.22
     でも
    -2.20
    饪
    -2.20
    
    -2.13
     Hinblick
    -2.06
    ᷆
    -2.05
    轵
    -2.03
     芝
    -2.02
    grandmother
    -1.98
    POSITIVE LOGITS
    ’
    3.66
    s
    2.80
    w
    2.56
     dizzy
    2.50
    …’
    2.44
    ’)
    2.44
     ‘
    2.44
    ㉗
    2.41
    !’
    2.30
    ’,
    2.23
    Activations Density 0.002%

    No Known Activations