© 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. 41-GEMMASCOPE-2-RES-262K
    7. 59268
    Prev
    Next
    INDEX
    Explanations

    saddles

    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_all/layer_41_width_262k_l0_big
    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
     eye
    0.43
     demarcation
    0.42
     Face
    0.40
     fort
    0.40
    养
    0.40
     conservation
    0.40
     Eye
    0.40
    ]}{\
    0.39
     conserv
    0.39
     Snow
    0.39
    POSITIVE LOGITS
     saddle
    1.91
     saddles
    1.79
     Saddle
    1.55
     sadd
    1.32
     Sadd
    1.29
    鞍
    1.13
     сед
    1.03
     sadde
    1.00
    addle
    0.86
     Satt
    0.75
    Activations Density 0.002%

    No Known Activations