© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 1726
    Prev
    Next
    INDEX
    Explanations

    recipe measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_16k_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
     creditors
    1.72
    妽
    1.70
    煂
    1.66
    晠
    1.66
     renamed
    1.66
    穸
    1.64
     farther
    1.62
    震
    1.62
    vdots
    1.61
     criminals
    1.60
    POSITIVE LOGITS
    1
    1.29
    one
    1.18
    一场
    1.05
    2
    1.02
    一份
    0.98
    3
    0.92
    0
    0.92
     one
    0.89
     μιας
    0.89
     العدد
    0.87
    Activations Density 0.159%

    No Known Activations