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

    Neuronpedia

    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. 110108
    Prev
    Next
    INDEX
    Explanations

    cleanser

    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
     (
    0.70
     leta
    0.64
     kra
    0.63
     ذ
    0.63
    （
    0.61
     vaccines
    0.58
    溽
    0.57
    が
    0.56
     azimuth
    0.55
    에
    0.55
    POSITIVE LOGITS
     ರಿಂದ
    0.55
    مي
    0.55
     purposefully
    0.55
     प्रसन्न
    0.54
    kinder
    0.54
    mone
    0.52
    நக
    0.50
    bate
    0.50
     RESON
    0.50
    මණ
    0.50
    Activations Density 0.002%

    No Known Activations