© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 16527
    Prev
    Next
    INDEX
    Explanations

    listing, continuation, etc

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly lights up on relatively uncommon or low‐frequency vocabulary—i.e. rare or technical words.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    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
     in
    -1.27
     so
    -1.20
    ditionally
    -1.16
     of
    -1.15
     on
    -1.12
     their
    -1.05
    ようになります
    -1.02
    breviation
    -1.02
     demografica
    -1.00
    «
    -0.96
    POSITIVE LOGITS
     and
    1.84
     etc
    1.74
    そして
    1.45
     และ
    1.38
    และ
    1.35
    などが
    1.20
     Könige
    1.08
    Spesifikasi
    1.06
    حتی
    1.06
    等等
    1.06
    Activations Density 0.058%

    No Known Activations