© 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. 50454
    Prev
    Next
    INDEX
    Explanations

    Interference, automation, remembrance

    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
    ählten
    0.48
     distributed
    0.47
    $-$
    0.47
     fray
    0.47
    jols
    0.46
     torno
    0.45
    Curso
    0.45
     phát
    0.44
     versões
    0.44
     使っ
    0.44
    POSITIVE LOGITS
    ं
    0.46
    ，
    0.44
    고
    0.44
    逐
    0.43
    。
    0.43
    旁邊
    0.42
    чої
    0.40
    第二天
    0.40
    сія
    0.39
    עד
    0.38
    Activations Density 0.001%

    No Known Activations