© 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-262K
    7. 51245
    Prev
    Next
    INDEX
    Explanations

    questions and clarifications

    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_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
    joy
    0.46
    😁
    0.46
    all
    0.45
    using
    0.43
     😁
    0.43
     Joy
    0.43
     ‘
    0.42
     :)
    0.41
    ple
    0.41
     problemlos
    0.40
    POSITIVE LOGITS
     atrocities
    0.48
     Ичиго
    0.46
     calamities
    0.45
    VerFile
    0.43
     vost
    0.42
     franchisee
    0.42
     ሳ
    0.42
     overcrowding
    0.42
     afterthought
    0.42
     mockery
    0.42
    Activations Density 0.000%

    No Known Activations