Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 8950
    Prev
    Next
    INDEX
    Explanations

    adding functionality or features

    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
    çou
    0.48
    skjaer
    0.47
     svært
    0.45
     peculiarly
    0.45
     you
    0.44
    śla
    0.44
    vell
    0.43
    🏘
    0.42
    opez
    0.42
     முழுவதும்
    0.42
    POSITIVE LOGITS
     hinzu
    1.09
     добавля
    0.94
     доба
    0.93
     add
    0.92
     adicion
    0.89
    添加
    0.88
     additional
    0.88
     добавить
    0.86
     hinzufügen
    0.84
     thêm
    0.84
    Activations Density 0.100%

    No Known Activations