© 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. 73851
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun noun

    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
     språk
    -1.45
     they
    -1.45
     REDUC
    -1.43
     bedien
    -1.40
    which
    -1.38
    ***/
    -1.38
     medlem
    -1.37
    as
    -1.36
    tons
    -1.35
    oooooo
    -1.35
    POSITIVE LOGITS
     to
    1.73
     of
    1.67
    That
    1.45
     Furthermore
    1.42
    Furthermore
    1.42
     italienischen
    1.40
     that
    1.39
    向了
    1.38
     furthermore
    1.38
     europäischen
    1.38
    Activations Density 0.018%

    No Known Activations