© 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. 108909
    Prev
    Next
    INDEX
    Explanations

    European currency or security features

    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
    é
    0.55
    t
    0.48
    ږئ
    0.46
    ллі
    0.44
    攻擊
    0.43
    etty
    0.43
    和服务
    0.42
    ग्गा
    0.42
    看
    0.42
    ulin
    0.42
    POSITIVE LOGITS
     дней
    0.50
    Mode
    0.44
    Materials
    0.43
     টিভির
    0.43
     corrugated
    0.43
     해야
    0.42
    ativement
    0.42
     Moż
    0.42
     নীতি
    0.42
    Prz
    0.41
    Activations Density 0.000%

    No Known Activations