© 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. 83909
    Prev
    Next
    INDEX
    Explanations

    he followed by words ending in -ology or participles

    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
    、“
    -2.98
    ，“
    -2.53
    $
    -2.50
    ”，
    -2.44
    </sup>
    -2.39
    “.
    -2.38
    ，”
    -2.36
    华为
    -2.31
    $'
    -2.30
    idelberg
    -2.28
    POSITIVE LOGITS
    0
    3.11
    1
    2.70
    ва
    2.48
    tedì
    2.44
    8
    2.36
    3
    2.34
    ep
    2.31
    he
    2.30
     —
    2.23
    >
    2.23
    Activations Density 0.022%

    No Known Activations