© 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. 180463
    Prev
    Next
    INDEX
    Explanations

    wife, owner

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

    frosting and falsifiability

    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
    kę
    0.54
    ī
    0.52
     लोकार्पण
    0.51
    ăș
    0.48
     구해
    0.47
     सेवाएं
    0.47
     alır
    0.47
     идут
    0.46
    ज़्
    0.46
    ử
    0.46
    POSITIVE LOGITS
    /*
    0.50
    Genre
    0.47
     Advocates
    0.45
     Omnibus
    0.44
    者
    0.44
     sarc
    0.44
     Os
    0.43
     "*.
    0.43
     ppm
    0.42
     Modem
    0.42
    Activations Density 0.001%

    No Known Activations