© 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. 34-GEMMASCOPE-RES-131K
    7. 62692
    Prev
    Next
    INDEX
    Explanations

    carpenter, carpet, and carpediem

    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
    苦
    -0.65
     optimum
    -0.64
    BaseResponse
    -0.64
    Theore
    -0.63
    총
    -0.63
     laajenta
    -0.63
     autoimmune
    -0.63
    瑤
    -0.62
     estatales
    -0.62
     Sí
    -0.61
    POSITIVE LOGITS
     diem
    0.92
     Diem
    0.91
    ENTER
    0.87
     Carpenter
    0.83
     Carp
    0.82
     кап
    0.81
    Carpenter
    0.79
    carp
    0.79
     Poplar
    0.78
    informationen
    0.77
    Activations Density 0.041%

    No Known Activations