© 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. 95620
    Prev
    Next
    INDEX
    Explanations

    email and shipping logistics

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

    not dangerous, not serious, not harmful

    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
    ців
    0.47
    ﮄ
    0.46
    творення
    0.46
     scaleOf
    0.44
    reportBody
    0.43
    veranst
    0.43
    ając
    0.42
    ंपेक्षा
    0.41
    Ꮆ
    0.41
    jobNumber
    0.41
    POSITIVE LOGITS
     manages
    0.54
     enzim
    0.51
     mgr
    0.49
     ham
    0.48
     spinal
    0.47
     malaria
    0.47
     mobile
    0.47
     milligrams
    0.47
     brewers
    0.47
     cholesterol
    0.47
    Activations Density 0.001%

    No Known Activations