© 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. 61753
    Prev
    Next
    INDEX
    Explanations

    Beyoncé or other celebrities

    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
     prion
    0.42
    ण्
    0.39
     pooch
    0.38
    獐
    0.38
    }}\|
    0.38
     Aqueous
    0.37
     problemática
    0.37
    الط
    0.37
     permas
    0.36
    ুল্য
    0.36
    POSITIVE LOGITS
     offspring
    0.41
     بھائی
    0.41
     belonged
    0.39
                       
    0.37
     instruct
    0.36
    …
    0.36
     progeny
    0.36
     більше
    0.35
    бир
    0.35
     বুকে
    0.35
    Activations Density 0.126%

    No Known Activations