© 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. 40-GEMMASCOPE-2-RES-262K
    7. 10790
    Prev
    Next
    INDEX
    Explanations

    training data

    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_40_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
    建て
    0.44
    ারের
    0.42
     पहिले
    0.42
    ারি
    0.41
     getActivity
    0.40
    <0x80>
    0.40
     firstly
    0.40
     wrapper
    0.40
     dover
    0.39
     നമഃ
    0.39
    POSITIVE LOGITS
     Trainings
    0.51
     تد
    0.51
    Train
    0.49
     regimens
    0.48
    綀
    0.46
    训练
    0.45
     trainers
    0.44
     Trainers
    0.44
    Training
    0.43
    訓練
    0.43
    Activations Density 0.035%

    No Known Activations