© 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. 143351
    Prev
    Next
    INDEX
    Explanations

    bits and Pepper

    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
     explode
    0.50
     ইনডাক
    0.47
     extérieur
    0.47
     ativar
    0.47
    嗥
    0.47
    车的
    0.46
    攻击
    0.46
    ফুল্ল
    0.46
     Explosion
    0.46
    紵
    0.46
    POSITIVE LOGITS
     niche
    0.47
    ەی
    0.42
     responsabil
    0.41
    []
    0.40
     credibility
    0.40
     thoughtfully
    0.40
     תו
    0.39
    (),
    0.39
    isement
    0.39
    nement
    0.38
    Activations Density 0.001%

    No Known Activations