© 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-16K
    7. 6740
    Prev
    Next
    INDEX
    Explanations

    conditional programming statements

    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_16k_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
    งาน
    1.26
    ル
    1.23
    மார
    1.17
    ER
    1.13
    ม
    1.11
     abhor
    1.09
    イン
    1.09
    ात
    1.08
     trotzdem
    1.07
    آ
    1.05
    POSITIVE LOGITS
    т
    1.26
    ص
    1.24
    с
    1.13
    ᅧ
    1.12
    ferencia
    1.11
     اینکه
    1.10
    დნენ
    1.08
    raham
    1.05
    ссии
    1.04
     حالات
    1.01
    Activations Density 0.059%

    No Known Activations