© 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. 56042
    Prev
    Next
    INDEX
    Explanations

    rights and laws

    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
     строго
    -0.89
     マイク
    -0.74
     микро
    -0.74
    きる
    -0.74
     Micro
    -0.72
     End
    -0.72
     Ende
    -0.71
     East
    -0.71
    Checks
    -0.70
    Full
    -0.69
    POSITIVE LOGITS
     fielder
    0.97
    Բ
    0.90
    ᥲ
    0.89
    ائب
    0.84
    مال
    0.82
     مسلم
    0.81
     ilustrasi
    0.81
     Fähigkeit
    0.81
     fikk
    0.80
    ザード
    0.79
    Activations Density 0.014%

    No Known Activations