© 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. 16-GEMMASCOPE-2-RES-262K
    4. 20999
    Prev
    Next
    INDEX
    Explanations

    dismantling things

    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_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
    of
    1.28
    나
    1.02
    のは
    1.01
    DI
    0.93
    DR
    0.91
    Domain
    0.91
    Data
    0.90
    Blockchain
    0.88
    ない
    0.86
    Seb
    0.82
    POSITIVE LOGITS
     dismantling
    1.34
    т
    1.14
    ور
    1.07
    <0xAD>
    1.05
     dismantled
    1.05
    <0x98>
    1.04
     agreg
    1.02
     equivoc
    1.01
     dismantle
    1.00
    ت
    1.00
    Activations Density 0.003%

    No Known Activations