© 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. 31-GEMMASCOPE-2-RES-65K
    7. 63251
    Prev
    Next
    INDEX
    Explanations

    new or novel concepts

    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_65k_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
    ਖ
    0.48
    ప
    0.47
     Sandra
    0.44
    خ
    0.43
    γ
    0.43
    ل
    0.43
    ﻓ
    0.42
     പുറ
    0.42
    ස
    0.42
    প
    0.41
    POSITIVE LOGITS
     mediast
    0.46
     grom
    0.46
     parab
    0.45
     cartil
    0.45
     pulmonary
    0.45
     contingencies
    0.44
    ु
    0.44
    注意事项
    0.43
     *.
    0.42
     .'
    0.42
    Activations Density 0.009%

    No Known Activations