© 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. 34-GEMMASCOPE-RES-131K
    7. 109098
    Prev
    Next
    INDEX
    Explanations

    words starting with roz

    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_34/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
    sigs
    -0.77
    politico
    -0.74
     circles
    -0.73
     silently
    -0.73
     prosz
    -0.72
    することに
    -0.72
    venture
    -0.71
    ＾＾；
    -0.71
    circles
    -0.71
    renti
    -0.69
    POSITIVE LOGITS
    pieler
    0.87
    naments
    0.84
     schuld
    0.80
    ﻌ
    0.80
     Dispatcher
    0.79
    ッタ
    0.77
     ';
    0.77
    Interview
    0.77
    劳
    0.77
    urrection
    0.77
    Activations Density 0.002%

    No Known Activations