© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 1471
    Prev
    Next
    INDEX
    Explanations

    respectively, glyphosate, glycine, glycerin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ي
    2.91
    й
    2.67
    та
    2.56
    да
    2.41
    り
    2.38
    ла
    2.34
    йки
    2.34
    ли
    2.25
    ᴏ
    2.23
    y
    2.22
    POSITIVE LOGITS
    ل
    1.77
     Reim
    1.55
     zeit
    1.53
     Jesu
    1.51
     demi
    1.48
     Oscill
    1.48
     kans
    1.48
     dú
    1.47
    게
    1.47
    ﻯ
    1.45
    Activations Density 0.063%

    No Known Activations