© 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. 65315
    Prev
    Next
    INDEX
    Explanations

    section headings

    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
     What
    -1.04
    What
    -0.93
     How
    -0.91
     what
    -0.90
     Does
    -0.87
     carta
    -0.85
     dici
    -0.80
     nera
    -0.80
     Have
    -0.79
     useful
    -0.77
    POSITIVE LOGITS
    <h3>
    1.84
    subsection
    1.76
    subsubsection
    1.53
    <h2>
    1.23
     ২
    1.09
     subsection
    1.09
     subsections
    0.94
    .),
    0.93
    Heute
    0.93
     angenehm
    0.92
    Activations Density 0.007%

    No Known Activations