© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35473
    Prev
    Next
    INDEX
    Explanations

    people in/from/who/of/whom

    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
    unknownFields
    -1.09
    buzo
    -1.07
    שְׁ
    -1.06
    ífero
    -1.06
     disponibile
    -1.06
    chiat
    -1.04
    牠
    -1.04
    \
    -1.00
     definição
    -1.00
    impre
    -1.00
    POSITIVE LOGITS
     who
    1.81
    cended
    1.23
    čky
    1.16
    ٣
    1.15
    Various
    1.15
    People
    1.12
    árbol
    1.10
    Mesmo
    1.09
    ynchronously
    1.05
     الذين
    1.02
    Activations Density 0.063%

    No Known Activations