© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30322
    Prev
    Next
    INDEX
    Explanations

    russian grammatical questions

    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
     Ezek
    -0.90
    Въ
    -0.87
    无论是
    -0.82
    福井
    -0.81
    minecraft
    -0.81
    　　-
    -0.80
     населення
    -0.80
     Grav
    -0.79
    近年来
    -0.79
     SERVER
    -0.79
    POSITIVE LOGITS
     hero
    1.45
     heroes
    1.36
     Hero
    1.03
     characters
    1.02
     readers
    0.99
     heroine
    0.96
    hero
    0.92
     images
    0.91
     social
    0.90
     trouve
    0.90
    Activations Density 0.005%

    No Known Activations