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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12270
    Prev
    Next
    INDEX
    Explanations

    acknowledging states like okay and worry

    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_16k_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
     avoid
    0.61
     Avoid
    0.56
     it
    0.54
     {
    0.53
     sweets
    0.53
     don
    0.51
     avoiding
    0.51
     Jill
    0.51
     !
    0.50
     believe
    0.50
    POSITIVE LOGITS
    midrule
    0.54
    के
    0.49
    Factor
    0.49
     الناتج
    0.49
    现在的
    0.48
    最も
    0.47
    소
    0.47
    ◍
    0.46
    ubic
    0.46
     რამდენ
    0.46
    Activations Density 0.144%

    No Known Activations