© 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. 22-GEMMASCOPE-RES-131K
    7. 73741
    Prev
    Next
    INDEX
    Explanations

    how to ask questions

    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_22/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
    hatsu
    -0.97
    こっち
    -0.93
     qualquer
    -0.92
     cualquiera
    -0.89
    ()][
    -0.89
    yorsunuz
    -0.89
     preparatory
    -0.87
    的原因
    -0.86
    REASONS
    -0.86
    メガネ
    -0.85
    POSITIVE LOGITS
     will
    1.49
     when
    1.39
    はどう
    1.34
     if
    1.34
    怎么办
    1.09
     how
    0.98
     who
    0.93
    when
    0.91
    怎麼辦
    0.90
    henden
    0.88
    Activations Density 0.101%

    No Known Activations