© 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. 193035
    Prev
    Next
    INDEX
    Explanations

    legal, Johnson, detected, coffee, ever

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

    sexual orientation, verses, poly, modeling, shadow

    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
    蟹
    0.47
    滗
    0.46
     韩
    0.45
     Withdraw
    0.45
    抻
    0.44
     Scorpion
    0.43
    闫
    0.42
    。<
    0.42
    ่ะ
    0.42
    韩
    0.42
    POSITIVE LOGITS
    postos
    0.49
     >
    0.45
     enam
    0.44
    ാപ
    0.43
    etry
    0.43
    ambiental
    0.42
    projekt
    0.42
     monumental
    0.42
    iae
    0.41
     જિલ્લા
    0.41
    Activations Density 0.001%

    No Known Activations