© 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. 63291
    Prev
    Next
    INDEX
    Explanations

    bird singing

    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
    वाइड
    0.43
    缉
    0.43
     הנו
    0.41
     сто
    0.41
     ketchup
    0.41
     화면
    0.39
     acronym
    0.39
     ሂ
    0.39
     dyslex
    0.39
    रेक्ट
    0.38
    POSITIVE LOGITS
     singing
    1.20
     chir
    0.93
     Singing
    0.87
     chirp
    0.86
    歌
    0.86
     सिंगिंग
    0.83
     birds
    0.82
     sings
    0.80
    唱歌
    0.79
     song
    0.78
    Activations Density 0.003%

    No Known Activations