© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15762
    Prev
    Next
    INDEX
    Explanations

    technical routinesmedical routinesdaily routines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    这里
    -2.88
    鴴
    -2.52
    蛲
    -2.47
    slika
    -2.38
    }^{
    -2.36
    蒾
    -2.33
    咴
    -2.31
    alamat
    -2.31
     ungewöhn
    -2.30
    謦
    -2.28
    POSITIVE LOGITS
    骉
    3.03
    '
    3.02
    孓
    2.72
    ſelves
    2.61
    の味
    2.56
    鴆
    2.55
     guardado
    2.33
     белом
    2.30
    n
    2.28
    を追加
    2.25
    Activations Density 0.005%

    No Known Activations