© 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-262K
    7. 7663
    Prev
    Next
    INDEX
    Explanations

    margin properties

    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
     withstand
    1.47
     devast
    1.40
     candid
    1.32
     conve
    1.25
     confront
    1.25
     molest
    1.25
    ,
    1.25
    Flo
    1.23
     gradu
    1.23
     consolid
    1.23
    POSITIVE LOGITS
    يل
    2.11
    dır
    1.88
    它
    1.88
    ます
    1.82
    ์
    1.77
    iy
    1.67
    aj
    1.66
    ição
    1.65
     さらに
    1.63
    ｉ
    1.60
    Activations Density 0.031%

    No Known Activations