© 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. 73474
    Prev
    Next
    INDEX
    Explanations

    speaker conversational text snippets

    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
     fucking
    -1.10
    fucking
    -1.03
    constexpr
    -1.02
    WindowConstants
    -1.01
    <tbody>
    -0.99
    ‍♂️
    -0.98
     dudes
    -0.96
     damn
    -0.96
    }{$
    -0.96
     sir
    -0.93
    POSITIVE LOGITS
    ค่ะ
    1.27
     colorear
    1.21
    Ekster
    1.16
    :"-
    1.13
     hubby
    1.09
     enseñar
    1.09
     ayudarte
    1.06
    ɞ
    1.05
     DH
    1.02
     bienvenida
    1.02
    Activations Density 0.039%

    No Known Activations