© 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. 32841
    Prev
    Next
    INDEX
    Explanations

    the superlative quality

    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
     but
    -1.55
     to
    -1.45
     and
    -1.40
     سایر
    -1.28
    其他
    -1.25
    vaila
    -1.15
     other
    -1.11
    ???:
    -1.06
    Ϳ
    -1.03
     anderen
    -1.02
    POSITIVE LOGITS
     best
    1.91
     necessary
    1.80
     needed
    1.53
    様な
    1.41
     required
    1.32
     desired
    1.32
    <b>
    1.28
     sufficient
    1.27
     adequate
    1.22
     appropriate
    1.20
    Activations Density 0.029%

    No Known Activations