© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10878
    Prev
    Next
    INDEX
    Explanations

    recommendations and ratings

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

    recommendation systems and personalized suggestions

    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_40_width_16k_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
     munt
    0.42
    Tunnel
    0.39
    雪
    0.39
     Pond
    0.38
    flake
    0.38
    akit
    0.38
    Snow
    0.37
    Transport
    0.37
     環
    0.37
     arh
    0.37
    POSITIVE LOGITS
    推薦
    0.76
     recommendation
    0.73
     ratings
    0.72
     rating
    0.72
     recomm
    0.70
     Personalized
    0.69
     Rating
    0.68
     Recommendation
    0.68
     recommend
    0.67
     추천
    0.67
    Activations Density 0.065%

    No Known Activations