Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 1112
    Prev
    Next
    INDEX
    Explanations

    revealing hidden information

    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
    ند
    2.06
    いっぱい
    1.91
    ই
    1.89
    ع
    1.85
    مم
    1.77
    بد
    1.74
     afield
    1.72
    いろんな
    1.69
    ين
    1.65
    ↵
    1.64
    POSITIVE LOGITS
     ση
    1.73
    ва
    1.72
    odeon
    1.66
    enquête
    1.66
     adanya
    1.65
    вной
    1.63
    йки
    1.62
    в
    1.58
    दार
    1.56
     phép
    1.56
    Activations Density 0.068%

    No Known Activations