© 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. 80
    Prev
    Next
    INDEX
    Explanations

    ancestral custom, seat, language, spirits, homeland, rights

    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
     ouvertes
    1.53
    ेंगे
    1.52
     brunes
    1.44
    藹
    1.39
     petting
    1.38
    たない
    1.36
    લ
    1.31
     effectuées
    1.30
    𝚢
    1.30
     loi
    1.28
    POSITIVE LOGITS
    ang
    1.91
    ра
    1.91
    ard
    1.74
    Image
    1.71
    osť
    1.65
    не
    1.59
     Въ
    1.58
    ine
    1.57
    ir
    1.56
    ні
    1.56
    Activations Density 0.007%

    No Known Activations