© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 1704
    Prev
    Next
    INDEX
    Explanations

    music and playlists

    np_acts-logits-general · gemini-2.5-flash-lite

    music and playlists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    cein
    0.43
    咳嗽
    0.42
     ক্ষত্র
    0.41
     fluorine
    0.40
    签字
    0.40
     배우
    0.39
     VFX
    0.39
    躓
    0.38
    ითხ
    0.38
     estructuras
    0.38
    POSITIVE LOGITS
     playlists
    1.40
     playlist
    1.39
     Spotify
    1.37
     music
    1.32
     Playlist
    1.29
    音乐
    1.26
     Music
    1.25
     음악
    1.24
     musik
    1.23
     muzy
    1.20
    Activations Density 0.332%

    No Known Activations