© 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. 77203
    Prev
    Next
    INDEX
    Explanations

    license text

    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
     seksi
    -0.99
     kado
    -0.89
    LAHOMA
    -0.88
     torba
    -0.88
    ώ
    -0.84
     materiaal
    -0.84
    llywood
    -0.82
     tane
    -0.82
     komment
    -0.82
     kyl
    -0.81
    POSITIVE LOGITS
      
    0.96
       
    0.82
    ച്ച
    0.78
    त
    0.72
     on
    0.72
    Review
    0.72
     goes
    0.70
     h
    0.65
    bia
    0.65
     Review
    0.65
    Activations Density 0.034%

    No Known Activations