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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 5386
    Prev
    Next
    INDEX
    Explanations

    dis or un prefixes

    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
    棦
    0.28
    一个
    0.26
    ოველ
    0.26
     attrs
    0.25
    ﻲ
    0.25
    You
    0.24
     LastName
    0.24
     transcriptome
    0.24
    它
    0.24
    您
    0.24
    POSITIVE LOGITS
    ac
    0.33
    de
    0.29
    ig
    0.28
    ag
    0.28
    dis
    0.28
     dis
    0.27
    un
    0.27
    az
    0.26
     displaced
    0.25
    ad
    0.25
    Activations Density 0.082%

    No Known Activations