© 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. 48786
    Prev
    Next
    INDEX
    Explanations

    singing and vocal performance

    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
     Encyclopædia
    0.45
    ॒
    0.45
    ẏ
    0.43
    ୍
    0.42
    ؟
    0.42
    berkeley
    0.42
    <sup>
    0.40
     ‌
    0.40
     fucking
    0.39
    🏽
    0.38
    POSITIVE LOGITS
     singer
    0.80
     singers
    0.79
     vocalist
    0.78
     singing
    0.78
     सिंगिंग
    0.76
     sing
    0.73
    唱歌
    0.72
     노래
    0.71
     cantante
    0.71
    歌手
    0.70
    Activations Density 0.000%

    No Known Activations