Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 2185
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    स
    1.11
     the
    1.07
    ال
    1.07
    ig
    1.01
    с
    1.01
     experiment
    1.00
    ড
    1.00
    ung
    0.99
     భాగంగా
    0.98
     некоторым
    0.98
    POSITIVE LOGITS
    ﻮ
    1.13
     MORE
    1.04
     biologiques
    1.01
     ロング
    0.98
     אור
    0.97
    ﺔ
    0.96
    ﻞ
    0.96
     REGULATIONS
    0.96
     Recherche
    0.94
    લાઇ
    0.94
    Activations Density 0.075%

    No Known Activations