© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 19
    Prev
    Next
    INDEX
    Explanations

    defines our societies. While

    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
     to
    0.80
     jokingly
    0.79
    𝚑
    0.76
     or
    0.74
     iban
    0.73
     कौशिक
    0.73
     legit
    0.73
    用来
    0.73
    ್ರೆ
    0.73
    または
    0.72
    POSITIVE LOGITS
     što
    0.81
    ruktur
    0.81
     behov
    0.77
     nécessité
    0.76
    sthe
    0.76
     četiri
    0.75
    とはいえ
    0.75
    ।
    0.74
    CONSUM
    0.73
     Arzneim
    0.72
    Activations Density 0.085%

    No Known Activations