© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 91762
    Prev
    Next
    INDEX
    Explanations

    hacked credit card

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     оборудование
    0.49
    𝐞
    0.48
    事业单位
    0.47
    設備
    0.46
    тено
    0.46
    ė
    0.46
    ेज
    0.45
    糍
    0.44
    hutang
    0.44
    irling
    0.44
    POSITIVE LOGITS
     oppure
    0.51
     protect
    0.50
     paio
    0.49
     poeta
    0.48
     letter
    0.47
     ovvero
    0.47
     k
    0.47
     natomiast
    0.47
     deine
    0.47
     verse
    0.45
    Activations Density 0.001%

    No Known Activations