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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 6071
    Prev
    Next
    INDEX
    Explanations

    expressing pleasure helping

    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_16_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
     It
    0.75
    il
    0.69
    eg
    0.67
    ung
    0.67
    uk
    0.67
    k
    0.66
    te
    0.66
    ik
    0.64
     आवश्यक
    0.64
    ram
    0.63
    POSITIVE LOGITS
     heartwarming
    0.89
    ید
    0.80
     overjoyed
    0.77
    きの
    0.73
    🥳
    0.72
    ாட்டு
    0.71
     delighted
    0.70
    де
    0.70
    да
    0.70
     smiling
    0.69
    Activations Density 0.162%

    No Known Activations