© 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. 144115
    Prev
    Next
    INDEX
    Explanations

    life, detergent, information, launch

    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
    거
    0.55
    ﻦ
    0.53
    禳
    0.45
    替え
    0.44
    разде
    0.44
    麓
    0.44
    트
    0.43
     ঘরে
    0.43
    ٹ
    0.42
     pecho
    0.42
    POSITIVE LOGITS
    ua
    0.49
     contas
    0.48
     produkt
    0.48
     sa
    0.48
     PSL
    0.48
     financials
    0.47
     aperta
    0.47
     demokrat
    0.46
     Zed
    0.46
     i
    0.46
    Activations Density 0.003%

    No Known Activations