© 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. 22-GEMMASCOPE-RES-131K
    7. 36589
    Prev
    Next
    INDEX
    Explanations

    programming imports

    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_22/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
    ﻹ
    -1.09
    Numerous
    -1.02
     that
    -0.98
     its
    -0.96
    endpush
    -0.96
    Before
    -0.96
     afirmó
    -0.94
    ésultat
    -0.93
     menyukai
    -0.93
     their
    -0.93
    POSITIVE LOGITS
    <th>
    1.05
    ‑
    1.02
    =\"
    0.99
    <td>
    0.97
    È
    0.96
    %</
    0.95
    🇬
    0.95
    埽
    0.94
    lij
    0.94
    ต้อง
    0.94
    Activations Density 0.004%

    No Known Activations