© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104098
    Prev
    Next
    INDEX
    Explanations

    individual context

    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
    }$
    -2.19
     enam
    -1.86
     alcune
    -1.82
    </b>
    -1.79
    </u>
    -1.77
     impo
    -1.74
     the
    -1.72
     Rezept
    -1.72
    ].
    -1.70
     intric
    -1.67
    POSITIVE LOGITS
     encompasses
    2.33
    𖡼
    2.16
    賡
    2.09
    甡
    2.06
    罍
    2.05
    Ᏻ
    2.02
    辚
    1.99
    vereignty
    1.98
    ⡪
    1.98
    ⚋
    1.97
    Activations Density 0.028%

    No Known Activations