© 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. 40-GEMMASCOPE-2-RES-262K
    4. 120427
    Prev
    Next
    INDEX
    Explanations

    vs. one-way

    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_40_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
     исход
    0.40
     сту
    0.39
     Sequencing
    0.38
     الصف
    0.37
    isub
    0.37
     sequenced
    0.37
    getInput
    0.36
    笃
    0.36
     অনুযায়ী
    0.36
     source
    0.36
    POSITIVE LOGITS
    ಿಸಲ
    0.42
     Ungarn
    0.40
    විය
    0.39
    Emails
    0.38
    vanja
    0.38
    墉
    0.38
    Investors
    0.37
    Ada
    0.36
    avanja
    0.36
    Bigl
    0.36
    Activations Density 0.001%

    No Known Activations