© 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. 100255
    Prev
    Next
    INDEX
    Explanations

    tan and Tam prefixes

    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
     of
    -3.66
    ႐
    -2.48
    𓆜
    -2.48
    趼
    -2.41
    ﮑ
    -2.39
    咵
    -2.31
     manajemen
    -2.27
    鹟
    -2.22
    蔸
    -2.19
     การ์ตูน
    -2.16
    POSITIVE LOGITS
    ⩖
    2.55
    1
    2.20
    ↵↵
    2.17
    ?
    2.17
    I
    2.09
     «
    2.03
    ном
    1.91
     —
    1.90
    ”
    1.81
    </h5>
    1.80
    Activations Density 0.001%

    No Known Activations