© 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. 83418
    Prev
    Next
    INDEX
    Explanations

    etymology and derivation

    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
    🍙
    -0.90
    خته
    -0.83
    jesz
    -0.81
     Į
    -0.81
    فقط
    -0.80
    ługi
    -0.79
    滇
    -0.78
    譎
    -0.78
     arxiv
    -0.78
     articular
    -0.78
    POSITIVE LOGITS
     derived
    3.27
     derives
    3.05
     derivation
    3.00
     Derived
    2.92
    derived
    2.84
     derive
    2.75
    Derived
    2.70
     deriv
    2.39
     Derivation
    2.27
    deriv
    2.25
    Activations Density 0.088%

    No Known Activations