© 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. 11965
    Prev
    Next
    INDEX
    Explanations

    India, Hindu, 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
     not
    -1.46
    kken
    -1.38
    ൎ
    -1.34
    呗
    -1.26
     keinen
    -1.21
     \
    -1.21
     tolerancia
    -1.20
     such
    -1.20
    からね
    -1.19
     وزارة
    -1.19
    POSITIVE LOGITS
    }$,
    1.48
     desnuda
    1.48
    <sup>
    1.38
    when
    1.35
     Даже
    1.33
     muerta
    1.33
    *}$
    1.31
     $^{
    1.31
    лось
    1.30
    适合
    1.29
    Activations Density 0.530%

    No Known Activations