© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 182468
    Prev
    Next
    INDEX
    Explanations

    dates and publications

    np_acts-logits-general · gemini-2.5-flash-lite

    selected images

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    i
    0.49
     rum
    0.49
     scab
    0.48
     lawyer
    0.47
     stev
    0.46
     butterfly
    0.46
     Showcase
    0.45
     gucci
    0.45
     showcase
    0.44
     catast
    0.44
    POSITIVE LOGITS
     கிரேக்க
    0.50
     वेरिएबल
    0.49
    нома
    0.47
     Appropri
    0.46
    夎
    0.46
     SELECTED
    0.45
    叵
    0.45
    ೭
    0.45
    Radiux
    0.44
     поверну
    0.44
    Activations Density 0.001%

    No Known Activations