© 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. 85465
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation or common conjunctions

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

    cost, illegal, activation

    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
     ghetto
    0.42
    ведена
    0.42
    habitude
    0.41
     സമീപ
    0.41
    gic
    0.40
    веден
    0.40
    РЕ
    0.40
     voisinage
    0.39
    ião
    0.39
     給
    0.39
    POSITIVE LOGITS
     dyspe
    0.45
     dieu
    0.45
     سید
    0.45
     दौ
    0.44
    larınız
    0.44
     itaque
    0.43
    พระ
    0.43
    कौन
    0.43
     yapı
    0.43
     peneliti
    0.43
    Activations Density 0.004%

    No Known Activations