© 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. 128029
    Prev
    Next
    INDEX
    Explanations

    nouns and abstract concepts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    j
    -1.20
    k
    -1.18
    H
    -1.16
    h
    -1.11
    m
    -1.06
    l
    -1.04
    v
    -1.03
    をご覧ください
    -1.02
    いろんな
    -0.99
     mattina
    -0.99
    POSITIVE LOGITS
     from
    1.27
     pulsera
    1.25
     Dě
    1.24
     fön
    1.21
     Accesorios
    1.21
    voer
    1.20
     snad
    1.19
    ipto
    1.16
     oraz
    1.14
     gorro
    1.14
    Activations Density 0.069%

    No Known Activations