© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118732
    Prev
    Next
    INDEX
    Explanations

    Cecelia Tichi

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    泄
    -0.83
     catal
    -0.79
    蟑
    -0.77
     nectar
    -0.76
    的首
    -0.74
    ваются
    -0.73
    JUL
    -0.72
     получила
    -0.71
     res
    -0.71
     cus
    -0.71
    POSITIVE LOGITS
     Cel
    0.91
     Ce
    0.74
     hammered
    0.72
    떤
    0.72
    шее
    0.71
    cette
    0.71
     derajat
    0.71
     Cet
    0.71
     closer
    0.70
     nutric
    0.69
    Activations Density 0.052%

    No Known Activations