© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41097
    Prev
    Next
    INDEX
    Explanations

    endings of words

    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
    ’
    -4.34
    ed
    -4.00
    is
    -3.58
    s
    -3.25
    d
    -3.23
    は
    -3.19
    on
    -3.17
    en
    -3.06
    的
    -2.95
    ized
    -2.91
    POSITIVE LOGITS
    鹛
    3.41
    飚
    3.08
    🦣
    3.06
    ة
    2.88
    鼍
    2.84
    ৹
    2.83
    熺
    2.83
    蹑
    2.81
    咴
    2.73
     onCreateView
    2.69
    Activations Density 0.124%

    No Known Activations