© 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. 16419
    Prev
    Next
    INDEX
    Explanations

    company names and establishments

    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
    createNewFile
    -1.30
    volen
    -1.20
     provas
    -1.18
    hålla
    -1.16
    ennials
    -1.13
    PASSWORD
    -1.13
    kraine
    -1.13
    tées
    -1.09
    ňov
    -1.09
    duino
    -1.09
    POSITIVE LOGITS
     name
    1.45
     establishments
    1.18
     நி
    1.16
     profile
    1.13
    erobic
    1.11
     establishment
    1.09
     business
    1.08
    設施
    1.02
     parlare
    1.01
    躋
    1.00
    Activations Density 0.026%

    No Known Activations