© 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. 32176
    Prev
    Next
    INDEX
    Explanations

    choices and outcomes

    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
    発
    0.48
     Oversight
    0.47
    faire
    0.41
    與
    0.41
    和
    0.41
    西
    0.40
    ilerden
    0.39
    晶
    0.39
     wiederum
    0.39
     poles
    0.39
    POSITIVE LOGITS
     impacto
    0.57
     dinâmica
    0.56
     retaliation
    0.55
     nama
    0.54
     hutan
    0.54
     Си
    0.52
     Qiu
    0.52
    tki
    0.52
     सिन
    0.52
     transformasi
    0.51
    Activations Density 0.000%

    No Known Activations