© 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. 122540
    Prev
    Next
    INDEX
    Explanations

    era, blogging, control

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

    keyword, brand, or ancient concepts

    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
    that
    0.57
    whose
    0.55
    to
    0.50
    Ho
    0.50
    P
    0.49
    Leng
    0.49
    Sz
    0.49
    l
    0.49
    Il
    0.48
    ema
    0.48
    POSITIVE LOGITS
     nutrit
    0.50
     patrim
    0.48
     pivoting
    0.47
     cuddling
    0.45
     गरीबों
    0.45
     tumultuous
    0.45
     overcrowding
    0.44
     scaffolding
    0.44
     nutritious
    0.44
     못한
    0.43
    Activations Density 0.001%

    No Known Activations