© 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. 152976
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases

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

    couple of

    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
     kakak
    0.44
    <0x90>
    0.43
    struck
    0.43
    tok
    0.42
     rivalry
    0.42
    soul
    0.42
     kond
    0.41
    concatenate
    0.41
     maîtres
    0.41
     Kons
    0.41
    POSITIVE LOGITS
    áo
    0.50
    ㅀ
    0.49
    Ⲓ
    0.47
    เปลี่ยนแปลง
    0.46
     এছাড়াও
    0.45
    බන්ධ
    0.45
    鬯
    0.45
    Continu
    0.44
     가능하다
    0.44
    นาะ
    0.44
    Activations Density 0.001%

    No Known Activations