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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30362
    Prev
    Next
    INDEX
    Explanations

    comic books and characters

    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
     care
    -0.82
    laboration
    -0.75
    ferenz
    -0.74
     seien
    -0.72
     seats
    -0.72
     washing
    -0.70
     Care
    -0.69
     pharynx
    -0.69
     mình
    -0.69
     Sti
    -0.69
    POSITIVE LOGITS
    Clone
    0.82
    kah
    0.77
     هایی
    0.75
    💉
    0.71
     McBride
    0.71
    Cros
    0.68
    ratings
    0.68
     Outback
    0.67
    loj
    0.66
    шаем
    0.66
    Activations Density 0.024%

    No Known Activations