© 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. 2154
    Prev
    Next
    INDEX
    Explanations

    `.com`, `.org`, `.gov`, `.py`

    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
    دید
    0.55
    cknowled
    0.54
    󰡔
    0.54
    Than
    0.50
    asă
    0.50
     Bedürfn
    0.48
     протяжении
    0.46
    čná
    0.46
    েদ
    0.45
    د
    0.45
    POSITIVE LOGITS
    კი
    0.52
    ても
    0.51
    槅
    0.50
    ك
    0.50
    rition
    0.49
    ว
    0.48
    karte
    0.48
    ou
    0.48
    ットン
    0.47
    कारी
    0.46
    Activations Density 0.603%

    No Known Activations