© 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. 210344
    Prev
    Next
    INDEX
    Explanations

    possession or object following pronoun

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

    Megawatt, specific snapshot, abnormal, your life

    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
    罵
    0.52
     Ј
    0.49
     monstrous
    0.48
    勝ち
    0.48
    に対し
    0.47
     Chatterjee
    0.47
    J
    0.46
     doub
    0.46
     respondent
    0.46
     spacetime
    0.46
    POSITIVE LOGITS
    TargetPath
    0.52
    acat
    0.47
    枨
    0.47
     금액
    0.46
     ремон
    0.46
    赠
    0.45
    对应的
    0.45
    Loan
    0.45
     قرض
    0.44
    abileceğ
    0.44
    Activations Density 0.000%

    No Known Activations