© 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. 180791
    Prev
    Next
    INDEX
    Explanations

    McGill, special agent, you keep

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

    needful, carapace, winners, secrets, Tomlinson, URL

    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
     ItemStack
    0.48
    TREE
    0.47
    &
    0.47
    敌
    0.44
    Done
    0.44
     June
    0.42
    ちなみに
    0.41
    Node
    0.41
    o
    0.41
     Lively
    0.40
    POSITIVE LOGITS
    ঵
    0.55
     vertebrates
    0.54
     bactéries
    0.52
     intensidade
    0.51
     diagnóstico
    0.51
     stent
    0.50
     teorías
    0.50
     reação
    0.49
     biomarkers
    0.49
     अल्ट्रा
    0.49
    Activations Density 0.000%

    No Known Activations