© 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. 10364
    Prev
    Next
    INDEX
    Explanations

    system, leader, or narrative elements

    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
     våra
    0.57
    髋
    0.57
    缐
    0.57
     পরিপ্রে
    0.56
    鈮
    0.55
     специфи
    0.54
    稦
    0.53
    沺
    0.52
    黉
    0.52
    柽
    0.52
    POSITIVE LOGITS
     murderous
    0.61
     despicable
    0.59
     nodded
    0.58
     humiliated
    0.57
     domine
    0.55
     muttered
    0.53
    ——
    0.53
     Ji
    0.52
     businessman
    0.52
     idiot
    0.52
    Activations Density 0.002%

    No Known Activations