© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 14468
    Prev
    Next
    INDEX
    Explanations

    orchestra

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    song
    0.64
    歌曲
    0.63
    Song
    0.56
     ऋ
    0.56
     song
    0.55
     teng
    0.55
    findOne
    0.54
     乳
    0.54
    rfloor
    0.54
     곡
    0.54
    POSITIVE LOGITS
     orchestra
    2.47
     Orchestra
    2.25
     orchestras
    2.25
    orche
    2.08
     orche
    1.95
     орке
    1.90
     Orche
    1.89
     symphony
    1.82
     ensemble
    1.74
     ensembles
    1.69
    Activations Density 0.079%

    No Known Activations