© 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. 747
    Prev
    Next
    INDEX
    Explanations

    sentence starters (Here, This, Let)

    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
    ۹
    1.17
    ক
    0.94
    ского
    0.93
    íncipe
    0.88
    년대
    0.87
     Ανακτήθηκε
    0.86
    ヤモンド
    0.85
    糁
    0.85
    ২
    0.84
    س
    0.83
    POSITIVE LOGITS
    ită
    1.00
    ం
    0.89
    u
    0.89
    age
    0.86
    ogeneous
    0.85
    arith
    0.84
    a
    0.83
    i
    0.82
    .}$
    0.82
     অন্যদিকে
    0.80
    Activations Density 0.520%

    No Known Activations