© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 129340
    Prev
    Next
    INDEX
    Explanations

    company names and entities

    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
    genöss
    -1.21
    にほんブログ村
    -1.20
     fevereiro
    -1.09
     December
    -1.07
     erschienen
    -1.06
     chega
    -1.03
     January
    -1.02
     ventajas
    -1.02
    قيقة
    -1.02
     potential
    -1.02
    POSITIVE LOGITS
     company
    1.77
     caricatura
    1.53
     familiale
    1.41
     شركة
    1.28
     companies
    1.24
     operations
    1.22
     family
    1.20
     étroite
    1.18
     services
    1.17
     rése
    1.16
    Activations Density 0.080%

    No Known Activations