© 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. 33024
    Prev
    Next
    INDEX
    Explanations

    explaining something in/by

    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
    に対して
    -0.96
     said
    -0.94
     mentioned
    -0.93
     dificil
    -0.92
     microfibra
    -0.91
    苤
    -0.91
    namics
    -0.88
     rua
    -0.88
     cripto
    -0.88
     raíz
    -0.87
    POSITIVE LOGITS
     in
    2.64
     by
    1.78
     below
    1.35
     herein
    1.34
     above
    1.26
     dalam
    1.14
     далее
    1.11
     on
    1.09
     earlier
    1.09
     therein
    1.06
    Activations Density 0.083%

    No Known Activations