© 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. 213315
    Prev
    Next
    INDEX
    Explanations

    linking descriptive words with subsequent nouns

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

    false identities or code blocks

    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
     Lights
    0.50
    甃
    0.48
    Boa
    0.47
     Pendant
    0.47
    ጠቀም
    0.47
     Complaints
    0.46
     Shoes
    0.46
    llllllll
    0.46
     Harness
    0.46
    lin
    0.45
    POSITIVE LOGITS
    то
    0.51
    ຽ
    0.50
     canned
    0.49
     condiment
    0.46
     cardiomyopathy
    0.46
     atypical
    0.45
     yada
    0.45
     содержа
    0.44
     ی
    0.44
     естественно
    0.44
    Activations Density 0.000%

    No Known Activations