© 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. 19651
    Prev
    Next
    INDEX
    Explanations

    themes and instructions

    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
     trajectories
    0.46
     annuities
    0.43
     obstructive
    0.42
     curation
    0.42
     systematic
    0.41
    Ⅴ
    0.41
     packing
    0.41
     locomotor
    0.41
    ｨ
    0.41
     opting
    0.41
    POSITIVE LOGITS
     सांगतात
    0.47
    ربون
    0.44
    kennung
    0.44
     különb
    0.43
    kter
    0.41
    說明
    0.39
     zuerst
    0.39
     يمكنك
    0.38
    멍
    0.38
     ين
    0.38
    Activations Density 0.027%

    No Known Activations