© 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. 16414
    Prev
    Next
    INDEX
    Explanations

    software and tools for domains

    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
     on
    -1.42
     for
    -1.21
     helps
    -1.18
     epitom
    -1.15
     as
    -1.15
    様が
    -1.06
    ấ
    -1.03
     coreano
    -1.02
     kühl
    -1.02
     naast
    -1.01
    POSITIVE LOGITS
    both
    1.33
    悻
    1.32
    unków
    1.25
    hradun
    1.20
     rimanere
    1.19
    different
    1.17
    such
    1.15
    还会
    1.13
    specifically
    1.13
     parteci
    1.10
    Activations Density 0.213%

    No Known Activations