© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 21737
    Prev
    Next
    INDEX
    Explanations

    flaxseed and linen

    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
    ăzi
    0.37
     изго
    0.36
    
    0.36
    кай
    0.36
    írás
    0.36
    íř
    0.36
    iph
    0.35
     hydrostatic
    0.35
    ỳ
    0.35
    Iran
    0.35
    POSITIVE LOGITS
     flax
    2.25
     linen
    2.13
     Flax
    2.02
     Linen
    1.98
    linen
    1.70
     linens
    1.39
     linseed
    1.26
     lin
    1.18
     LIN
    1.12
     Lin
    1.09
    Activations Density 0.004%

    No Known Activations