© 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. 44292
    Prev
    Next
    INDEX
    Explanations

    content image or header path

    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
     are
    -2.13
    蛲
    -2.08
    耵
    -1.98
     mensen
    -1.85
    毟
    -1.80
     sinyal
    -1.80
    桫
    -1.77
     potrebné
    -1.71
     pomocou
    -1.71
     kolek
    -1.70
    POSITIVE LOGITS
    </em>
    2.55
    </h2>
    2.00
     $\&$
    1.88
     \&
    1.81
     條
    1.74
    𖤍
    1.74
    ミー
    1.73
    勤務
    1.72
    ↵↵
    1.71
    ).
    1.64
    Activations Density 0.057%

    No Known Activations