© 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. 12380
    Prev
    Next
    INDEX
    Explanations

    legal prosecution and prosecutors

    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
     codecs
    0.43
     ஆராய்ச்சி
    0.42
     কার্যকরী
    0.41
     coordinated
    0.40
     headquarters
    0.39
     generates
    0.38
     热
    0.38
     avatar
    0.38
    딥
    0.38
     способствует
    0.37
    POSITIVE LOGITS
     prosecution
    1.41
     Prosecution
    1.38
     prosecutor
    1.34
    Prosec
    1.30
     prosecutors
    1.28
     Prosecutor
    1.23
     prosecuting
    1.23
     Prosecutors
    1.19
    Prosecutors
    1.13
     prosec
    1.02
    Activations Density 0.007%

    No Known Activations