© 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. 10-GEMMASCOPE-RES-131K
    7. 101927
    Prev
    Next
    INDEX
    Explanations

    written by or coined by

    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
    }
    -2.64
    The
    -2.45
    It
    -2.16
    .
    -1.98
    ”
    -1.98
     you
    -1.88
    ">>
    -1.87
     höheren
    -1.85
    autorelease
    -1.82
    читать
    -1.81
    POSITIVE LOGITS
    泂
    2.83
    欵
    2.69
    撄
    2.41
    沕
    2.39
    漚
    2.38
    ໊
    2.11
    with
    2.09
    of
    2.08
     trabaja
    2.05
    普通的
    2.05
    Activations Density 0.004%

    No Known Activations