© 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. 6348
    Prev
    Next
    INDEX
    Explanations

    faster than

    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
    triple
    0.41
    </h2>
    0.38
    time
    0.38
    Triple
    0.36
    圈
    0.36
    Big
    0.36
     নিশ্চিত
    0.36
     હાઉસ
    0.35
    Bought
    0.35
     అంటే
    0.34
    POSITIVE LOGITS
     tanpa
    0.44
     unsupported
    0.42
    ቓ
    0.42
     recomenda
    0.42
     Bahasa
    0.41
     jezik
    0.41
     bás
    0.41
     usuários
    0.41
    EnglishMarks
    0.40
    não
    0.39
    Activations Density 0.000%

    No Known Activations