© 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. 9166
    Prev
    Next
    INDEX
    Explanations

    heatmap, clustering, branching, matching

    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
     ต
    1.15
    нд
    1.14
     biển
    1.14
    𝐏
    1.13
     ร
    1.13
     ความ
    1.13
     rebound
    1.11
    teurs
    1.11
    Сегодня
    1.10
     அளித்த
    1.10
    POSITIVE LOGITS
     phospholipids
    1.24
    s
    1.21
    мо
    1.12
    ıları
    1.10
     presumptive
    1.08
    }$).
    1.07
    }\|_{
    1.04
    两者
    1.04
    ве
    1.02
    ्स
    1.02
    Activations Density 0.000%

    No Known Activations