© 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. 12122
    Prev
    Next
    INDEX
    Explanations

    prefix-suffix word completion

    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
     Wählen
    -1.84
    猹
    -1.79
     Itália
    -1.75
    ר
    -1.74
     seguimos
    -1.74
    襌
    -1.73
    ׁ
    -1.70
    餮
    -1.70
     проек
    -1.69
     polícia
    -1.69
    POSITIVE LOGITS
    Additionally
    1.89
     the
    1.80
    Ideally
    1.79
    嚳
    1.79
    with
    1.79
    commonly
    1.77
     PUSTAKA
    1.76
    become
    1.73
    Initially
    1.73
    にほんブログ村
    1.72
    Activations Density 0.000%

    No Known Activations