© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 20047
    Prev
    Next
    INDEX
    Explanations

    registration requirements

    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
     parecía
    0.60
     politič
    0.58
    政治
    0.55
    机遇
    0.52
    我觉得
    0.52
     करणारे
    0.52
    ⵕ
    0.52
     políticos
    0.51
    राजनी
    0.51
    瑟
    0.51
    POSITIVE LOGITS
     WhatsApp
    0.67
     duly
    0.64
     согласно
    0.63
     Whatsapp
    0.63
     Registration
    0.62
     whatsapp
    0.60
     sesuai
    0.60
     registration
    0.59
     SMS
    0.59
     반드시
    0.59
    Activations Density 0.043%

    No Known Activations