© 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. 31-GEMMASCOPE-2-RES-16K
    4. 3223
    Prev
    Next
    INDEX
    Explanations

    margin of error

    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_16k_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
     самый
    0.38
    _
    0.35
     Pine
    0.35
     ரோ
    0.35
     Irvine
    0.35
    <0xB5>
    0.34
    <0xF0>
    0.34
     rape
    0.34
     النا
    0.33
     Casper
    0.33
    POSITIVE LOGITS
     زیرمه
    0.36
     सहित
    0.36
     muttered
    0.36
    didn
    0.35
    presumably
    0.35
    quisitos
    0.35
    barui
    0.35
    urably
    0.34
    辏
    0.34
     paredes
    0.33
    Activations Density 0.694%

    No Known Activations