© 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. 34-GEMMASCOPE-RES-131K
    4. 119369
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by body parts

    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_34/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
    }).
    -0.93
     svoje
    -0.88
    ']).
    -0.84
     np
    -0.84
     aujourd
    -0.81
    цент
    -0.81
    ğlık
    -0.81
     willst
    -0.80
     here
    -0.79
     nebo
    -0.79
    POSITIVE LOGITS
     free
    1.16
     بدأ
    0.93
     other
    0.91
     fatis
    0.90
     Италии
    0.83
    Free
    0.83
    ینی
    0.82
    รส
    0.82
     roughly
    0.82
     diser
    0.82
    Activations Density 0.014%

    No Known Activations