© 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. 75759
    Prev
    Next
    INDEX
    Explanations

    mimicry and Mime types

    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
    Kval
    -0.84
    џ
    -0.81
    ранее
    -0.75
    اولة
    -0.73
     reuse
    -0.73
    Jeder
    -0.72
    ściu
    -0.70
    ematica
    -0.69
     licor
    -0.69
     macaroni
    -0.69
    POSITIVE LOGITS
     Mim
    1.13
     MIM
    0.96
    mim
    0.94
    Mim
    0.93
     mim
    0.91
     mime
    0.91
    Tn
    0.88
     Mime
    0.84
    hejiang
    0.83
    ANCING
    0.82
    Activations Density 0.015%

    No Known Activations