© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43284
    Prev
    Next
    INDEX
    Explanations

    contract definitions, followed by name

    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
     —
    -2.89
    es
    -2.73
    er
    -2.25
    b
    -2.23
    年中
    -2.22
     }
    -2.16
    Its
    -2.11
    It
    -2.11
     \\
    -2.09
    f
    -2.06
    POSITIVE LOGITS
    '
    2.50
    ࿙
    2.31
    サイクル
    2.30
    マリー
    2.06
    身边的
    2.05
    llten
    2.05
    是
    1.99
    ﺢ
    1.98
    jadwal
    1.98
    屃
    1.95
    Activations Density 0.000%

    No Known Activations