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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 642
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and owned items

    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
     "
    -1.83
     to
    -1.82
     by
    -1.69
     into
    -1.61
     they
    -1.56
     in
    -1.55
    ,
    -1.49
     or
    -1.48
     see
    -1.44
     and
    -1.43
    POSITIVE LOGITS
     numerose
    1.55
     cuando
    1.52
     attenzione
    1.50
    ώ
    1.48
     hermosas
    1.45
    思议
    1.45
    (‘
    1.44
    However
    1.43
     proposte
    1.41
     metálica
    1.41
    Activations Density 0.140%

    No Known Activations