© 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. 68735
    Prev
    Next
    INDEX
    Explanations

    rebirth, reincarnation, again

    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
    泚
    -2.73
    </strong>
    -2.59
    </h3>
    -2.52
    拊
    -2.52
    of
    -2.42
    あー
    -2.42
    えっ
    -2.30
    踯
    -2.25
     anc
    -2.17
    そりゃ
    -2.17
    POSITIVE LOGITS
     Because
    2.56
    There
    2.52
     Like
    2.33
     Surprisingly
    2.27
     With
    2.23
     Unlike
    2.23
    Like
    2.22
     Now
    2.17
     Since
    2.16
     in
    2.14
    Activations Density 0.006%

    No Known Activations