© 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. 144313
    Prev
    Next
    INDEX
    Explanations

    common English prepositions, numbers, abbreviations

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

    clarification or definition

    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
    Upgrade
    0.51
     poder
    0.45
    upgrade
    0.45
    ABSTRACT
    0.45
    ς
    0.43
    ्यक्रम
    0.43
     }$
    0.42
     ءِ
    0.42
    dioxide
    0.42
    devDependencies
    0.41
    POSITIVE LOGITS
    ili
    0.55
    ien
    0.54
    ır
    0.51
    ెల
    0.45
     edilmesi
    0.45
     sorting
    0.45
     créé
    0.45
    ard
    0.45
    ən
    0.44
    erea
    0.44
    Activations Density 0.001%

    No Known Activations