© 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. 53-GEMMASCOPE-2-RES-262K
    4. 18522
    Prev
    Next
    INDEX
    Explanations

    here are a bunch of

    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_53_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
    nip
    0.42
    NIC
    0.37
     penet
    0.37
     mek
    0.36
    廓
    0.36
    फलता
    0.36
    الف
    0.36
    厈
    0.36
     monastery
    0.35
     penetrating
    0.35
    POSITIVE LOGITS
    otechn
    0.38
     Capp
    0.38
     возникает
    0.36
     Artur
    0.36
     Sever
    0.35
     πίνα
    0.35
     écrite
    0.35
     ব্রি
    0.35
     আর্ম
    0.35
     Vatic
    0.35
    Activations Density 0.005%

    No Known Activations