© 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. 63509
    Prev
    Next
    INDEX
    Explanations

    housing and locations

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

    difficult, massive, public

    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
    Negative Logits
     Natural
    0.47
    끌
    0.46
     natural
    0.44
     vale
    0.44
    ร์
    0.44
    ยก
    0.44
     AS
    0.43
    ә
    0.43
     ASD
    0.42
    رین
    0.42
    POSITIVE LOGITS
    }.$$
    0.55
     आजमा
    0.54
    mere
    0.54
     जाऊन
    0.52
     முறையாக
    0.52
    मिला
    0.52
    mis
    0.52
    loss
    0.51
    meli
    0.50
     создает
    0.50
    Activations Density 0.000%

    No Known Activations