© 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. 53-GEMMASCOPE-2-RES-65K
    7. 4485
    Prev
    Next
    INDEX
    Explanations

    number of bedrooms

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

    p = or /

    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_53_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
    䣫
    0.47
     ਦਵਾਈ
    0.43
    裨
    0.43
    ﭜ
    0.43
     कल्चर
    0.43
     لاءِ
    0.42
     무료
    0.42
     அவருடைய
    0.42
    摀
    0.41
    饌
    0.41
    POSITIVE LOGITS
    rs
    0.72
    rm
    0.69
    ns
    0.69
    nt
    0.68
    td
    0.67
    pt
    0.67
    nd
    0.66
    ct
    0.64
    kt
    0.64
    mp
    0.64
    Activations Density 0.043%

    No Known Activations