© 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. 15108
    Prev
    Next
    INDEX
    Explanations

    Germany and German words

    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
    ある
    2.13
     וא
    2.02
    あります
    1.74
    قه
    1.73
     그래도
    1.73
    ك
    1.68
    於
    1.65
    mals
    1.63
    ถ่าย
    1.63
    乎
    1.55
    POSITIVE LOGITS
    б
    2.61
    ן
    2.50
    ﻨ
    2.22
    ৫
    2.16
    м
    2.11
    унд
    2.09
    ल
    2.08
    ны
    2.03
    н
    2.02
    ০
    2.02
    Activations Density 0.052%

    No Known Activations