© 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. 40-GEMMASCOPE-2-RES-262K
    7. 132959
    Prev
    Next
    INDEX
    Explanations

    Autobots, seismic protection

    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
     srd
    0.42
     ():
    0.41
     šť
    0.40
     gruppi
    0.39
     ஆம்
    0.39
     loại
    0.39
     grupos
    0.39
    أة
    0.39
    `).
    0.38
     Spell
    0.38
    POSITIVE LOGITS
     suspected
    0.39
    hesus
    0.38
     ಸ್ಥಾನ
    0.38
    oplane
    0.37
    ermat
    0.36
    Vecchio
    0.36
    当該
    0.35
    मैट
    0.35
    ophone
    0.34
    fighting
    0.34
    Activations Density 0.003%

    No Known Activations