© 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. 375
    Prev
    Next
    INDEX
    Explanations

    battling

    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
     mein
    1.23
     monsieur
    1.13
    知道
    1.08
     Celle
    1.05
     doctoral
    1.04
    を有する
    1.02
    を有
    1.01
     o
    1.00
    comed
    0.98
    ╫
    0.98
    POSITIVE LOGITS
     běž
    1.24
     проблеми
    1.13
    檛
    1.12
    ﻨ
    1.11
    ਰੀ
    1.09
     낮
    1.06
    ণ
    1.06
    ا
    1.05
    覧
    1.03
    лық
    1.02
    Activations Density 0.005%

    No Known Activations