© 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. 119893
    Prev
    Next
    INDEX
    Explanations

    various endings to common prefixes/roots

    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
     else
    -1.72
    </h3>
    -1.66
    ’;
    -1.62
    “
    -1.57
     that
    -1.57
    ”;
    -1.55
    </h1>
    -1.55
    ?”
    -1.51
    =“
    -1.51
    甡
    -1.49
    POSITIVE LOGITS
     "
    2.00
    䜣
    1.90
     истории
    1.87
    érieurs
    1.83
    戋
    1.81
    geſ
    1.78
    或者是
    1.76
     his
    1.75
    Život
    1.75
    ioare
    1.74
    Activations Density 0.207%

    No Known Activations