© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4036
    Prev
    Next
    INDEX
    Explanations

    informal contractions and slang

    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_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
    il
    1.67
    ів
    1.59
    c
    1.54
    ﻭ
    1.41
    ron
    1.38
    و
    1.38
    ść
    1.37
    it
    1.34
    ור
    1.27
    or
    1.26
    POSITIVE LOGITS
    Ef
    1.11
     त्यात
    1.10
    ajouter
    0.98
     Obec
    0.97
     Każ
    0.97
    zwischen
    0.96
    𝑬
    0.96
    滉
    0.96
     sorta
    0.96
     gemeinsamen
    0.96
    Activations Density 0.069%

    No Known Activations