© 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. 24-GEMMASCOPE-2-RES-16K
    7. 1897
    Prev
    Next
    INDEX
    Explanations

    coercion, violence, humiliation, and threshold

    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_24_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
    ă
    0.85
     utilises
    0.82
    긁
    0.81
    Psalm
    0.81
    Poems
    0.80
    T
    0.79
    Æ
    0.79
    р
    0.78
    অ
    0.77
    J
    0.77
    POSITIVE LOGITS
    тным
    0.78
     поскольку
    0.71
     Landschaft
    0.70
     dispuestos
    0.70
     amacıyla
    0.67
     القاعدة
    0.64
     valoración
    0.63
    volle
    0.63
     учетом
    0.63
     совпада
    0.62
    Activations Density 0.002%

    No Known Activations