© 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. 150073
    Prev
    Next
    INDEX
    Explanations

    possessive nouns and following punctuation

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

    rounds raised, locations, many people

    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
    ทด
    0.52
    旪
    0.48
     tarafından
    0.47
     olla
    0.46
    㗁
    0.45
     tas
    0.44
     দ্বারা
    0.44
    רו
    0.44
     epilepsy
    0.43
    рика
    0.43
    POSITIVE LOGITS
    anément
    0.57
    ἷ
    0.54
    лій
    0.49
     shrouded
    0.48
    LONDON
    0.47
    会議
    0.45
    loggedIn
    0.45
     години
    0.45
    acées
    0.44
    MARINE
    0.44
    Activations Density 0.000%

    No Known Activations