© 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. 45264
    Prev
    Next
    INDEX
    Explanations

    how to get things done

    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
     efectuar
    0.86
     그리고
    0.79
    그리고
    0.79
     undue
    0.77
     regra
    0.77
     ਅਤੇ
    0.76
    刈
    0.76
     outra
    0.74
     unnecessarily
    0.74
     donc
    0.73
    POSITIVE LOGITS
    aguars
    0.84
    oyant
    0.73
    hower
    0.71
     Alkaline
    0.69
    ubs
    0.68
    我
    0.66
    Lightning
    0.66
    🌫
    0.66
    的地
    0.65
    isko
    0.64
    Activations Density 0.000%

    No Known Activations