© 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. 34-GEMMASCOPE-RES-131K
    7. 63441
    Prev
    Next
    INDEX
    Explanations

    subject or focus of attention

    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
     Jian
    -0.73
     initComponents
    -0.71
     マルチ
    -0.70
    воря
    -0.69
    regado
    -0.69
     bie
    -0.69
     Epp
    -0.68
     Fem
    -0.68
    Beam
    -0.68
     Beam
    -0.67
    POSITIVE LOGITS
     subject
    5.31
    subject
    4.22
     object
    3.70
     subjects
    3.45
    Subject
    3.41
     Subject
    3.36
     objeto
    3.27
     oggetto
    3.11
    SUBJECT
    3.03
     objects
    2.89
    Activations Density 0.185%

    No Known Activations