© 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. 170339
    Prev
    Next
    INDEX
    Explanations

    common prepositions followed by nouns

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

    specific analysis book metrics track mystery patient

    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
    과는
    0.53
     افرادی
    0.51
    𝓁
    0.49
     exibir
    0.47
    を利用
    0.46
     Apesar
    0.46
    圓
    0.45
    λλ
    0.45
    ους
    0.45
     Torr
    0.45
    POSITIVE LOGITS
    yeong
    0.49
     butter
    0.48
    eting
    0.47
     denim
    0.47
     bestselling
    0.46
     ornith
    0.46
     Ober
    0.45
    OfThe
    0.44
    शेद
    0.44
     codes
    0.43
    Activations Density 0.001%

    No Known Activations