© 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. 16-GEMMASCOPE-2-RES-262K
    7. 6776
    Prev
    Next
    INDEX
    Explanations

    eggs

    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
    '
    0.77
     développe
    0.72
     possède
    0.68
    ală
    0.67
    arın
    0.65
     tremble
    0.63
     është
    0.62
     može
    0.61
    は
    0.61
     développ
    0.60
    POSITIVE LOGITS
     Eggs
    0.69
    2
    0.68
     Egg
    0.66
    0
    0.65
    4
    0.60
    8
    0.60
    9
    0.58
     Map
    0.56
     eggs
    0.56
    eggs
    0.55
    Activations Density 0.006%

    No Known Activations