© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 34002
    Prev
    Next
    INDEX
    Explanations

    seconds and energy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aj
    0.62
    incing
    0.61
    á
    0.58
    asi
    0.57
    ts
    0.56
    í
    0.56
    urro
    0.55
    j
    0.55
    alt
    0.55
    os
    0.54
    POSITIVE LOGITS
     ВИ
    0.59
     kiosk
    0.58
     HIM
    0.57
     whenever
    0.57
     appalling
    0.56
     amazement
    0.56
     breach
    0.55
     институт
    0.55
     ރ
    0.55
     bullets
    0.55
    Activations Density 0.002%

    No Known Activations