© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 164676
    Prev
    Next
    INDEX
    Explanations

    numbers, lists, specific individuals

    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_40_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
    Angleterre
    0.45
     ENGLAND
    0.42
     England
    0.42
    England
    0.41
    乃
    0.41
     उपर
    0.40
    Norway
    0.40
     ներ
    0.39
    antiate
    0.38
    Controller
    0.38
    POSITIVE LOGITS
     wished
    0.48
     grinned
    0.41
     Wishing
    0.37
    тивных
    0.37
    าลัย
    0.36
     😁
    0.35
     quería
    0.35
     jardin
    0.35
    ල
    0.35
     hỏi
    0.35
    Activations Density 0.000%

    No Known Activations