© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68140
    Prev
    Next
    INDEX
    Explanations

    place names ending in stan

    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
    檮
    -3.05
    渽
    -2.52
    閦
    -2.39
    佧
    -2.33
    倥
    -2.33
     shunned
    -2.30
    フェス
    -2.28
     dà
    -2.27
    eschön
    -2.25
    Of
    -2.20
    POSITIVE LOGITS
    ’
    3.94
    ↵↵
    3.28
    {
    3.19
    ↵
    2.78
    ”
    2.66
     ”
    2.56
    .
    2.52
    ]
    2.44
    」
    2.14
    のは
    2.09
    Activations Density 0.012%

    No Known Activations