© 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. 5237
    Prev
    Next
    INDEX
    Explanations

    paved trails or paths

    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
     أيضاً
    1.85
     учета
    1.85
    ce
    1.80
    ati
    1.77
    リ
    1.69
    nt
    1.65
    -
    1.63
    ली
    1.63
     എന്നാല്‍
    1.61
    ’
    1.61
    POSITIVE LOGITS
    ва
    2.25
    kannya
    2.22
    ным
    1.99
    いく
    1.97
    ﺭ
    1.96
    سازی
    1.87
    دة
    1.84
    ్‌
    1.84
     cherish
    1.77
    um
    1.74
    Activations Density 0.010%

    No Known Activations