© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54383
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and names

    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
    varez
    -0.87
     AQUÍ
    -0.85
    فوائد
    -0.81
    antung
    -0.80
    صدق
    -0.77
     Redacción
    -0.76
    消毒
    -0.76
    IndentedString
    -0.75
    アーティスト
    -0.74
    uncios
    -0.73
    POSITIVE LOGITS
     its
    2.11
    Its
    1.30
     Its
    1.21
    使其
    1.10
     jego
    1.10
     её
    1.09
     ее
    1.05
    その
    1.04
     její
    1.02
    与其
    0.98
    Activations Density 0.212%

    No Known Activations