© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 62024
    Prev
    Next
    INDEX
    Explanations

    project access and expiry

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

    repository or service definitions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ز
    0.61
    کی
    0.57
    สูง
    0.57
    কর
    0.54
    د
    0.53
    ین
    0.49
    करने
    0.49
    রণ
    0.49
    صفر
    0.49
    ัด
    0.49
    POSITIVE LOGITS
     disgusted
    0.53
     toil
    0.53
     attributing
    0.52
     godly
    0.51
     helplessly
    0.50
     gai
    0.50
     thugs
    0.50
     clic
    0.49
    i
    0.49
     sentimento
    0.48
    Activations Density 0.000%

    No Known Activations