© 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. 101620
    Prev
    Next
    INDEX
    Explanations

    files, folders, code

    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_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
     gas
    0.43
     acid
    0.42
     bell
    0.42
    エー
    0.40
    resize
    0.39
    gas
    0.38
    ↵↵
    0.37
    iomanip
    0.36
    arrival
    0.36
    acid
    0.36
    POSITIVE LOGITS
    ແມ
    0.52
     ఇప్పటికే
    0.51
     मजेदार
    0.50
     برابر
    0.48
    流畅
    0.47
    henderit
    0.46
     ძ
    0.45
     gradioApp
    0.45
     અને
    0.45
     सरकारी
    0.45
    Activations Density 0.006%

    No Known Activations