© 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. 22-GEMMASCOPE-RES-131K
    7. 32791
    Prev
    Next
    INDEX
    Explanations

    constant recurrence

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Cx
    -1.00
     ayudará
    -0.98
     berikutnya
    -0.98
     necesita
    -0.94
     contribuye
    -0.93
    setViewName
    -0.93
     grosser
    -0.93
    pegno
    -0.89
    Удачи
    -0.88
     após
    -0.88
    POSITIVE LOGITS
     permanent
    1.29
    perma
    1.25
     constantly
    1.23
     constant
    1.23
     every
    1.22
     instead
    1.17
     all
    1.16
    ตลอด
    1.14
     continual
    1.11
     rather
    1.06
    Activations Density 0.123%

    No Known Activations