© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 23500
    Prev
    Next
    INDEX
    Explanations

    instruction tuning

    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
    ومی
    0.46
    主动
    0.45
    一个
    0.44
    一個
    0.40
    Connector
    0.39
    苏
    0.39
    因为
    0.39
    蘇
    0.39
    קי
    0.38
    ложить
    0.38
    POSITIVE LOGITS
    werden
    0.46
    reise
    0.45
    aper
    0.44
    seem
    0.43
     verwendeten
    0.43
     commentary
    0.42
    bye
    0.42
     tinge
    0.42
    time
    0.42
    rising
    0.42
    Activations Density 0.001%

    No Known Activations