© 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. 118065
    Prev
    Next
    INDEX
    Explanations

    Class AAA, plaintiff, Q:

    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
    疎
    -0.79
     deutschland
    -0.73
     reng
    -0.72
    lliant
    -0.72
    民国
    -0.71
    karna
    -0.70
     Clearance
    -0.69
    explore
    -0.68
     Interesting
    -0.68
     colab
    -0.68
    POSITIVE LOGITS
     VFX
    0.75
    CARACTERIST
    0.73
     sarco
    0.73
     měli
    0.73
     Yogi
    0.73
     estudiar
    0.72
    棋
    0.71
    뻗
    0.71
    스터
    0.71
     corneal
    0.70
    Activations Density 0.009%

    No Known Activations