© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 2401
    Prev
    Next
    INDEX
    Explanations

    do or are questions

    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_16_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
    ,
    0.50
    m
    0.46
     σε
    0.43
    ligence
    0.43
    ต์
    0.41
    mals
    0.41
    тным
    0.41
    zzles
    0.40
    ない
    0.40
    naden
    0.40
    POSITIVE LOGITS
     nowy
    0.43
     Ünivers
    0.41
    კი
    0.41
     Üniversitesi
    0.40
    1
    0.39
    の世界
    0.38
    ﻜ
    0.38
     città
    0.37
     大学
    0.36
     ünivers
    0.36
    Activations Density 0.257%

    No Known Activations