© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81028
    Prev
    Next
    INDEX
    Explanations

    "I" expressing feelings or actions

    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
     différences
    -1.02
    ḿ
    -1.02
     circonstances
    -1.01
     usar
    -0.99
    爱好
    -0.97
     навсегда
    -0.95
    onos
    -0.95
    ould
    -0.93
    athers
    -0.92
     😉
    -0.91
    POSITIVE LOGITS
     know
    1.43
     feel
    1.41
     just
    1.33
     want
    1.30
     sometimes
    1.29
     often
    1.19
     feels
    1.17
    なのに
    1.07
     constantly
    1.05
     відчу
    1.05
    Activations Density 0.050%

    No Known Activations