© 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. 31-GEMMASCOPE-2-RES-262K
    7. 139461
    Prev
    Next
    INDEX
    Explanations

    original model weights

    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_31_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
    কার্য
    0.48
     succeeding
    0.44
     twor
    0.44
    vou
    0.44
     sensitized
    0.44
     vou
    0.42
     tomorrow
    0.42
    炇
    0.42
    摞
    0.42
    azolid
    0.41
    POSITIVE LOGITS
    ೆಂಟ್
    0.44
     रुका
    0.41
    どこ
    0.41
    کروچ
    0.41
     Большая
    0.40
    ӑ
    0.39
     सीखना
    0.39
    ুলি
    0.38
    ባድ
    0.38
    ζ
    0.38
    Activations Density 0.005%

    No Known Activations