© 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. 40-GEMMASCOPE-2-RES-262K
    7. 35839
    Prev
    Next
    INDEX
    Explanations

    accused, charged, convicted, arrested

    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_40_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
    捋
    0.42
     ఉత్ప
    0.41
    が増
    0.39
    院士
    0.39
     elastic
    0.38
     цер
    0.38
    átku
    0.38
     થ
    0.37
     purify
    0.37
     വേദ
    0.37
    POSITIVE LOGITS
     defendants
    1.34
     defendant
    1.27
     accused
    1.16
     convicted
    1.16
    被告
    1.14
     Defendant
    1.07
     arrested
    1.06
    Defendant
    1.05
     codef
    1.05
     अभियुक्त
    1.05
    Activations Density 0.011%

    No Known Activations