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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19182
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by association

    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
    Beskrivning
    -1.59
     we
    -1.39
    Our
    -1.35
     pirm
    -1.31
    },
    -1.30
    Zubereitung
    -1.30
     literaria
    -1.29
     of
    -1.27
     would
    -1.26
    Beskrivelse
    -1.23
    POSITIVE LOGITS
     obrázok
    1.41
     qualifi
    1.20
     ə
    1.18
    瞻
    1.17
     JTextField
    1.17
     })
    1.14
    officially
    1.14
    performed
    1.14
     demostr
    1.13
    discovered
    1.13
    Activations Density 0.141%

    No Known Activations