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. 247443
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     aside
    0.49
    ator
    0.49
    t
    0.48
    i
    0.46
    ol
    0.46
    im
    0.44
     In
    0.42
     Uns
    0.42
     immortal
    0.42
     conditionally
    0.42
    POSITIVE LOGITS
    ネルギー
    0.48
    襷
    0.48
    られる
    0.47
     충
    0.46
     चैंपियनशिप
    0.45
    喧
    0.45
    OVERRIDES
    0.45
     शक्ती
    0.45
    िक्स
    0.44
     തിരിച്ച
    0.44
    Activations Density 0.001%

    No Known Activations