© 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. 123784
    Prev
    Next
    INDEX
    Explanations

    Mohamed or Mohammed names

    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
    “
    -4.03
    2
    -3.58
    z
    -3.53
    1
    -3.52
    3
    -3.42
    8
    -3.39
    A
    -3.36
    「
    -3.36
    t
    -3.14
    ''
    -3.11
    POSITIVE LOGITS
    姈
    3.41
    ⢫
    3.25
    嵎
    3.11
    椟
    3.09
    脔
    2.84
    栒
    2.83
    鐒
    2.81
    狴
    2.81
    alakip
    2.80
    烀
    2.72
    Activations Density 0.002%

    No Known Activations