© 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. 67066
    Prev
    Next
    INDEX
    Explanations

    wage law, product bundles, film premieres, spending, deadlines, gambling, people profiles, topics, cooking

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

    a, is, or, '

    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
    dictionary
    0.41
     मान्य
    0.40
    -'
    0.40
     banter
    0.39
     Dictionary
    0.39
    span
    0.39
     ł
    0.39
     przedsi
    0.38
     inmue
    0.38
    "
    0.38
    POSITIVE LOGITS
    र्मेंद्र
    0.48
    হেল
    0.47
    ˣ
    0.44
    लेखित
    0.41
    ônica
    0.41
    toni
    0.41
    lefthar
    0.40
     mRNAs
    0.40
    ডো
    0.40
     MPH
    0.40
    Activations Density 0.001%

    No Known Activations