© 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. 7775
    Prev
    Next
    INDEX
    Explanations

    float left

    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
    TryDecode
    -2.14
    </b>
    -2.00
     verdaderamente
    -1.99
     Saltar
    -1.91
    ↵↵
    -1.82
    箆
    -1.71
    咙
    -1.70
     الطعام
    -1.68
     воспользова
    -1.66
    在自己
    -1.64
    POSITIVE LOGITS
    </h3>
    2.53
    𓋼
    2.22
    an
    2.19
    ～～
    2.13
    ]
    2.11
    ～～～
    2.00
    ～♪
    1.85
    ֟
    1.83
     și
    1.82
     và
    1.77
    Activations Density 0.009%

    No Known Activations