© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47029
    Prev
    Next
    INDEX
    Explanations

    recursive sorting and merging

    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
     관계로
    0.48
    晧
    0.47
    皓
    0.43
    یده
    0.43
    belum
    0.42
     ectopic
    0.42
    ामुळे
    0.42
    edent
    0.41
     အတွ
    0.41
    امین
    0.41
    POSITIVE LOGITS
     T
    0.55
     mime
    0.50
     U
    0.48
    a
    0.48
     Z
    0.45
     COT
    0.45
     τε
    0.44
     butcher
    0.44
     monit
    0.44
     Vy
    0.43
    Activations Density 0.001%

    No Known Activations