© 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. 10-GEMMASCOPE-RES-131K
    4. 1419
    Prev
    Next
    INDEX
    Explanations

    paying and its rewards

    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_10/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
     it
    -1.94
     how
    -1.49
    IFORNIA
    -1.47
     have
    -1.38
     will
    -1.33
    ]=$
    -1.30
    ouchers
    -1.29
    ώ
    -1.27
     únicas
    -1.23
     there
    -1.23
    POSITIVE LOGITS
    If
    1.55
     millennia
    1.38
     Câ
    1.33
     afferma
    1.30
    Ꮠ
    1.28
     douane
    1.27
    かったので
    1.27
    瓩
    1.27
    ms
    1.25
    来て
    1.25
    Activations Density 0.013%

    No Known Activations