© 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-262K
    4. 244127
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    oten
    0.49
    oted
    0.49
    hension
    0.48
    pler
    0.47
    vis
    0.47
     >>>
    0.47
    confident
    0.47
    versing
    0.47
     अत
    0.46
     fhe
    0.46
    POSITIVE LOGITS
    ్
    0.54
    贞
    0.53
    contains
    0.46
    ról
    0.45
    িক্ত
    0.42
     talál
    0.42
    ينية
    0.42
    ুতে
    0.42
     Stevie
    0.41
    িক্যাল
    0.40
    Activations Density 0.000%

    No Known Activations