© 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. 22-GEMMASCOPE-RES-131K
    7. 72428
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by attributes

    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
    ’
    -1.39
    minos
    -1.34
    fordshire
    -1.33
    letics
    -1.32
    ׳
    -1.29
    strator
    -1.28
    rsquo
    -1.27
    tonsoft
    -1.22
    aneous
    -1.18
    licante
    -1.17
    POSITIVE LOGITS
     expertise
    1.81
     knowledge
    1.69
     experience
    1.46
     skills
    1.36
     know
    1.36
     resources
    1.23
    経験
    1.16
     years
    1.13
     previous
    1.13
    元々
    1.09
    Activations Density 0.028%

    No Known Activations