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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 8171
    Prev
    Next
    INDEX
    Explanations

    lady or ladies

    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
    ির
    2.66
    ى
    2.17
    ق
    2.16
    т
    2.00
    ت
    1.84
    تان
    1.82
    ب
    1.82
    но
    1.70
    og
    1.69
     déc
    1.68
    POSITIVE LOGITS
    nection
    2.25
    AK
    2.19
    ꜰ
    2.14
    se
    2.09
     espero
    2.08
     Gaga
    2.08
    αυ
    2.08
     Infatti
    2.06
     gemakkelijk
    2.05
    ۔
    2.03
    Activations Density 0.022%

    No Known Activations