© 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. 38063
    Prev
    Next
    INDEX
    Explanations

    technical file fragments

    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
    -1.02
    While
    -0.92
     through
    -0.91
     even
    -0.90
     their
    -0.89
     an
    -0.89
     while
    -0.88
     found
    -0.87
     usually
    -0.85
     climático
    -0.85
    POSITIVE LOGITS
     ダーク
    1.02
     amulet
    0.97
     Tuk
    0.96
    ouflage
    0.95
     パール
    0.93
    Thé
    0.93
    Meno
    0.91
     PERMAN
    0.91
    Fré
    0.90
    Lact
    0.89
    Activations Density 0.000%

    No Known Activations