© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 39899
    Prev
    Next
    INDEX
    Explanations

    lists of things including numbers

    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_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
    check
    0.43
    ad
    0.40
    rod
    0.40
     modo
    0.39
     induct
    0.39
    offic
    0.39
     powy
    0.38
     D
    0.38
    querySelector
    0.38
    모델
    0.38
    POSITIVE LOGITS
     nejen
    0.48
    ！”
    0.48
     পৰ
    0.46
    ],”
    0.46
    Hamburger
    0.46
     국제
    0.45
    International
    0.44
    遗憾
    0.44
    IsNull
    0.43
    tał
    0.43
    Activations Density 0.007%

    No Known Activations