© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 145839
    Prev
    Next
    INDEX
    Explanations

    burning off crop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     ergonomics
    0.78
    asov
    0.74
     පිළිබ
    0.70
    ò
    0.70
     നടപ
    0.69
    秚
    0.69
     చర్య
    0.69
     Pache
    0.69
    enov
    0.67
     আওয়ামী
    0.67
    POSITIVE LOGITS
    widet
    0.74
    шт
    0.72
    ށ
    0.70
    汞
    0.69
     ft
    0.67
    イド
    0.67
     gyárt
    0.67
    gruppen
    0.66
     οποίο
    0.66
     gen
    0.65
    Activations Density 0.000%

    No Known Activations