© 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. 20480
    Prev
    Next
    INDEX
    Explanations

    Ig, Bia, Agbaje, Ashland, LAN

    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
    焄
    -2.23
     They
    -2.13
    ⪧
    -2.02
    ⩴
    -1.98
    馋
    -1.98
    イケ
    -1.84
     общей
    -1.84
    ୩
    -1.83
    群体
    -1.83
     –
    -1.83
    POSITIVE LOGITS
    釭
    2.39
    )
    2.36
    {
    2.25
    晄
    2.22
     You
    2.03
     exemplified
    1.98
     they
    1.97
    佯
    1.90
     senjata
    1.83
    "
    1.80
    Activations Density 0.003%

    No Known Activations