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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 30336
    Prev
    Next
    INDEX
    Explanations

    cold + related terms

    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
    ла
    0.57
    ン
    0.57
    啰
    0.53
    ikannya
    0.52
    esu
    0.50
    н
    0.50
    મ
    0.50
    elang
    0.49
    eper
    0.49
    سٹم
    0.49
    POSITIVE LOGITS
     Ι
    0.68
    fifty
    0.63
     precept
    0.62
     Into
    0.61
     เยอะ
    0.58
     introducir
    0.57
     Individ
    0.57
     frío
    0.56
     convertirse
    0.56
     dieci
    0.56
    Activations Density 0.005%

    No Known Activations