© 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. 88524
    Prev
    Next
    INDEX
    Explanations

    testing/measured by units

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

    past tense verbs and modal verbs

    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
    stick
    0.46
    fahr
    0.46
     larga
    0.45
    ぷ
    0.44
     rapide
    0.44
    buttonclick
    0.43
    契約
    0.43
    hardware
    0.43
    らい
    0.42
    굉
    0.42
    POSITIVE LOGITS
    党员
    0.49
    离子
    0.47
     الأصفر
    0.46
    য়র
    0.46
     doğru
    0.44
    alnız
    0.44
     খাও
    0.43
     обстоятельства
    0.42
     நார்
    0.42
    宝宝
    0.42
    Activations Density 0.001%

    No Known Activations