© 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. 31-GEMMASCOPE-2-RES-16K
    7. 3569
    Prev
    Next
    INDEX
    Explanations

    <start_of_turn> or end of utterance

    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_31_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
    ゼロ
    0.55
    invalidate
    0.52
    经典
    0.51
     annular
    0.51
    结
    0.51
     गैर
    0.50
    हारिक
    0.50
     positional
    0.49
    肚子
    0.49
    ختار
    0.48
    POSITIVE LOGITS
     Wouldn
    0.60
     }^{\
    0.55
    ),]),
    0.55
     Hercegov
    0.54
     こちら
    0.53
     🥰
    0.52
     Daarnaast
    0.52
     Couldn
    0.51
     اللّه
    0.50
     Сьогодні
    0.50
    Activations Density 0.745%

    No Known Activations