© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72380
    Prev
    Next
    INDEX
    Explanations

    Portuguese possessive pronouns followed by technical terms

    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_10/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
     rozpoczę
    -2.22
    INGHAM
    -2.14
    quelize
    -2.14
     wobec
    -2.13
    ),
    -2.09
    “
    -2.09
    謦
    -2.08
    会不会
    -2.05
     is
    -2.03
    YOND
    -2.00
    POSITIVE LOGITS
     referrerpolicy
    2.11
     akin
    2.06
    籥
    2.00
    焢
    1.93
     посмотреть
    1.90
    .’
    1.85
    силання
    1.84
     indicative
    1.84
     も
    1.81
    ご了承
    1.80
    Activations Density 0.001%

    No Known Activations