© 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. 6387
    Prev
    Next
    INDEX
    Explanations

    Prep time and media types

    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
    ভাই
    0.38
    ㅉ
    0.36
    லிய
    0.35
    RefreshToken
    0.35
    仟
    0.34
     itemView
    0.34
    ggg
    0.33
    ۴
    0.33
    ალაქ
    0.33
    <unused74>
    0.33
    POSITIVE LOGITS
     ¼
    0.41
     _
    0.38
    ¼
    0.38
     halt
    0.36
     dail
    0.35
     Some
    0.35
     Those
    0.34
     Ο
    0.34
     models
    0.34
     ۱۰
    0.34
    Activations Density 0.004%

    No Known Activations