© 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. 127974
    Prev
    Next
    INDEX
    Explanations

    UCLA, Los Angeles, Bruins

    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
    他的
    -2.70
    ípio
    -2.42
    瞜
    -2.34
     Если
    -2.31
    類似
    -2.22
    Ꮟ
    -2.22
     Misalnya
    -2.20
    縂
    -2.17
     компания
    -2.16
    ཫ
    -2.16
    POSITIVE LOGITS
    which
    2.48
    _
    2.34
    ↵
    2.34
    蘼
    2.20
    凩
    2.17
    𓋼
    2.16
    m
    2.00
    你先
    1.98
    鹛
    1.98
     tne
    1.98
    Activations Density 0.002%

    No Known Activations