© 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. 53-GEMMASCOPE-2-RES-262K
    7. 49921
    Prev
    Next
    INDEX
    Explanations

    Marian, Marion, Mariana

    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_53_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
    லக
    0.40
    Чем
    0.38
     Чем
    0.38
    ysł
    0.38
    los
    0.38
    每
    0.37
     မှာ
    0.37
     mọi
    0.37
     每
    0.37
    ประจำ
    0.36
    POSITIVE LOGITS
    Marion
    0.54
    naud
    0.53
     Marian
    0.51
    Marian
    0.50
     Marion
    0.48
    ette
    0.45
    apolis
    0.45
    Mari
    0.43
     Marianne
    0.43
     Mariana
    0.41
    Activations Density 0.001%

    No Known Activations