© 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. 73596
    Prev
    Next
    INDEX
    Explanations

    Accountants seldom

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

    South China Sea

    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
    ☻
    0.44
    يريا
    0.43
    Kann
    0.42
     bebê
    0.41
    ॐ
    0.40
    🥤
    0.40
    ヾ
    0.40
    🥛
    0.40
    ારી
    0.40
    ອ
    0.40
    POSITIVE LOGITS
     nhưng
    0.44
     seldom
    0.42
     however
    0.42
     Admiralty
    0.42
     indeed
    0.41
     Champs
    0.41
     Accounting
    0.40
     lesser
    0.40
     narrower
    0.40
     Accountants
    0.40
    Activations Density 0.004%

    No Known Activations