© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91608
    Prev
    Next
    INDEX
    Explanations

    adding information

    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
     чесно
    -0.98
     we
    -0.90
    Produktion
    -0.85
     meille
    -0.84
     manna
    -0.83
    podob
    -0.83
    Życiorys
    -0.82
    mischer
    -0.82
    شتی
    -0.82
     propuesto
    -0.82
    POSITIVE LOGITS
     adding
    3.23
     noting
    2.81
     added
    2.56
     add
    2.19
    adding
    2.06
    添加
    2.05
     доба
    2.00
     adds
    1.94
     saying
    1.89
     Adding
    1.88
    Activations Density 0.022%

    No Known Activations