© 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. 178834
    Prev
    Next
    INDEX
    Explanations

    sales controlling, compliance, events

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

    amounts and increase

    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
    exercises
    0.52
     modalities
    0.46
    ！（
    0.46
    一块
    0.46
    machines
    0.45
    mite
    0.45
    두
    0.45
    平衡
    0.43
     Бі
    0.43
     फ्लावर
    0.43
    POSITIVE LOGITS
     окон
    0.46
     został
    0.45
     recibió
    0.44
    łoży
    0.44
     recib
    0.43
     stoked
    0.43
     debtors
    0.43
     Astrid
    0.43
     Prim
    0.42
    łożyć
    0.42
    Activations Density 0.000%

    No Known Activations