© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 235758
    Prev
    Next
    INDEX
    Explanations

    residence, remodeling, washing

    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
    다면
    0.39
    }{$\
    0.39
     Luật
    0.39
     legalize
    0.39
    deviation
    0.38
    follow
    0.37
    ylabel
    0.37
     Consecutive
    0.36
    ].)
    0.36
     takip
    0.36
    POSITIVE LOGITS
     palaces
    0.47
     życia
    0.47
     gorges
    0.46
     mnie
    0.46
     جدید
    0.44
     życiu
    0.43
    هران
    0.43
     cz
    0.42
     maisons
    0.42
     کیلوم
    0.42
    Activations Density 0.001%

    No Known Activations