© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102746
    Prev
    Next
    INDEX
    Explanations

    Scor, Amal, Clooney, Yuki, Lyme

    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
    ’
    -3.58
     —
    -2.66
    '
    -2.56
    d
    -2.55
    ’,
    -2.53
     cambiar
    -2.33
    ,’
    -2.28
    )}
    -2.25
     vond
    -2.25
    }}{\
    -2.23
    POSITIVE LOGITS
    小结
    2.30
    俢
    2.25
     شیپور
    2.22
    鋮
    2.20
    étais
    2.20
    蒾
    2.20
    はコチラ
    2.17
    ௜
    2.17
     sprüche
    2.17
    acterísticas
    2.17
    Activations Density 0.012%

    No Known Activations