© 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-262K
    7. 3036
    Prev
    Next
    INDEX
    Explanations

    labor costs and exploitation

    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
    ia
    2.25
    ó
    2.14
    il
    2.08
    ak
    1.90
    mesi
    1.89
    i
    1.89
    ok
    1.81
    ah
    1.74
     maneras
    1.73
    ió
    1.73
    POSITIVE LOGITS
     silicate
    1.93
    Ле
    1.84
    ة
    1.83
    Baş
    1.82
    𝐀
    1.78
    Ἀ
    1.74
    нең
    1.73
    Пер
    1.70
     gentamicin
    1.70
    Př
    1.63
    Activations Density 0.003%

    No Known Activations