© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 113693
    Prev
    Next
    INDEX
    Explanations

    foreign banks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ')->
    0.48
    -
    0.47
    A
    0.47
    LP
    0.46
    لیل
    0.46
    ISH
    0.46
    SG
    0.45
    SIN
    0.45
     صہیونیوں
    0.44
    тон
    0.44
    POSITIVE LOGITS
     банки
    0.57
     indirectly
    0.52
     బ్యాంకు
    0.49
     rozhod
    0.49
     банков
    0.48
    频
    0.47
     банка
    0.46
     ব্যাংক
    0.46
     stupidity
    0.46
    进了
    0.44
    Activations Density 0.000%

    No Known Activations