© 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. 25008
    Prev
    Next
    INDEX
    Explanations

    common collocations following activating word

    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
    sekten
    -1.23
    ίος
    -1.13
    Guests
    -1.13
    गु
    -1.13
    ension
    -1.12
    ciech
    -1.12
     quinze
    -1.10
    tagHelper
    -1.10
    eight
    -1.09
    tová
    -1.08
    POSITIVE LOGITS
     at
    1.48
     ontstaan
    1.41
    amerikanischer
    1.31
     creía
    1.27
    omalainen
    1.26
     brengen
    1.25
     rangkaian
    1.21
    有些不
    1.21
    ִּ
    1.20
    снимок
    1.20
    Activations Density 0.019%

    No Known Activations