© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 9421
    Prev
    Next
    INDEX
    Explanations

    blast to the past

    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
    由
    0.86
    ين
    0.84
    એ
    0.82
    ับ
    0.75
    애
    0.72
    隐藏
    0.71
    为了
    0.71
    后续
    0.69
    从
    0.69
    inscription
    0.69
    POSITIVE LOGITS
     deodor
    0.99
     payoffs
    0.98
     kiosks
    0.94
     rankings
    0.91
     diarrhea
    0.91
     primates
    0.90
     smartphones
    0.88
     shortages
    0.88
    ಥವಾ
    0.87
    nows
    0.87
    Activations Density 0.000%

    No Known Activations