© 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. 49904
    Prev
    Next
    INDEX
    Explanations

    I statements and 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
    THEOREM
    -1.04
    فين
    -0.97
     utilizzato
    -0.96
    حد
    -0.96
     ورو
    -0.95
    켭
    -0.94
     scelto
    -0.94
    jue
    -0.94
    也非常
    -0.93
    ار
    -0.93
    POSITIVE LOGITS
     likes
    1.79
     loves
    1.52
     drink
    1.45
     like
    1.44
     wear
    1.38
     love
    1.37
     wears
    1.31
     worship
    1.30
     use
    1.27
     coleccion
    1.19
    Activations Density 0.090%

    No Known Activations