© 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-65K
    7. 7666
    Prev
    Next
    INDEX
    Explanations

    snow and winter

    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_65k_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
     July
    0.56
     June
    0.51
    癀
    0.50
    July
    0.48
     PDT
    0.47
     জুন
    0.45
     june
    0.45
     julio
    0.45
    夏の
    0.45
    绀
    0.45
    POSITIVE LOGITS
     snow
    1.76
     winter
    1.71
    ❄
    1.63
    ☃
    1.60
     겨울
    1.55
    ⛄
    1.54
    winter
    1.52
    Winter
    1.51
     invierno
    1.49
    雪
    1.48
    Activations Density 0.133%

    No Known Activations