© 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. 35932
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns (her, his, their)

    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
    これを
    -1.28
     пароль
    -1.28
    でしょうね
    -1.26
    などは
    -1.20
     камень
    -1.14
    рою
    -1.14
    これは
    -1.13
    と思いました
    -1.11
     apartament
    -1.10
    これが
    -1.09
    POSITIVE LOGITS
    為に
    1.59
    感じが
    1.34
    感じで
    1.33
    ݯ
    1.27
    ほうが
    1.27
    つづく
    1.26
    ,
    1.22
    ܇
    1.21
     name
    1.20
     rechazar
    1.20
    Activations Density 0.034%

    No Known Activations