© 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. 16764
    Prev
    Next
    INDEX
    Explanations

    collocations forming phrases

    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
     lurking
    -1.18
    Gentile
    -1.09
    Pian
    -1.09
    规矩
    -1.05
     arou
    -1.05
     perplexing
    -1.03
    Beskrivelse
    -1.02
     disconcer
    -1.01
    Helena
    -1.00
    鉚
    -1.00
    POSITIVE LOGITS
     your
    1.38
    \_
    1.23
     our
    1.19
     a
    1.16
    probably
    1.10
    criminate
    1.09
    maybe
    1.08
    ¦
    1.08
    Š
    1.06
     the
    1.05
    Activations Density 0.004%

    No Known Activations