© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60913
    Prev
    Next
    INDEX
    Explanations

    Galaxy model names

    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
    </sup>
    -2.08
    ."
    -1.70
    </h4>
    -1.70
    </strong>
    -1.68
     This
    -1.66
    </em>
    -1.63
     тоже
    -1.61
    </h2>
    -1.60
    ities
    -1.58
     sahen
    -1.55
    POSITIVE LOGITS
    鱨
    1.88
     of
    1.81
    甞
    1.55
    缑
    1.55
    絰
    1.46
     ordini
    1.45
     Kommentare
    1.42
     obtenir
    1.41
    ꜄
    1.41
     reprez
    1.40
    Activations Density 0.005%

    No Known Activations