© 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. 130776
    Prev
    Next
    INDEX
    Explanations

    sheep, AD, controller, GVC

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

    seller and media

    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
    p
    0.45
     universe
    0.44
     width
    0.43
     valet
    0.43
     penalty
    0.42
    -
    0.42
    ни
    0.41
     watery
    0.41
     scatter
    0.41
     polar
    0.40
    POSITIVE LOGITS
    𝗥
    0.55
     niewiel
    0.51
     ორი
    0.50
     മിക
    0.50
     வேளா
    0.50
     मीट
    0.50
     نہیں۔
    0.49
     बॅ
    0.49
     クロ
    0.48
     جیک
    0.48
    Activations Density 0.001%

    No Known Activations