© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 2130
    Prev
    Next
    INDEX
    Explanations

    listing items after punctuation

    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_65k_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
     pizzas
    0.40
    包括
    0.37
     फिट
    0.36
    🍣
    0.35
    ={}
    0.34
    各种
    0.34
     গ্রন্থে
    0.33
     molécules
    0.33
    ভাগে
    0.33
    🍪
    0.33
    POSITIVE LOGITS
    Miscellaneous
    0.56
     miscellaneous
    0.55
     activism
    0.52
     Miscellaneous
    0.50
     journalism
    0.50
     interpersonal
    0.50
     humanities
    0.50
     conspiracy
    0.49
     procedural
    0.48
     comedy
    0.48
    Activations Density 0.887%

    No Known Activations