© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2758
    Prev
    Next
    INDEX
    Explanations

    songs and soundtracks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_16k_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
    ∅
    0.69
    イッチ
    0.68
    crate
    0.67
     WAT
    0.65
     warehousing
    0.64
     experimentation
    0.64
     الفوت
    0.62
     빈
    0.62
     Experiments
    0.62
     Blot
    0.62
    POSITIVE LOGITS
     song
    3.38
     songs
    3.28
     Song
    2.77
     Songs
    2.75
    song
    2.73
    Song
    2.72
     canciones
    2.72
    songs
    2.70
    歌曲
    2.69
    Songs
    2.66
    Activations Density 0.362%

    No Known Activations