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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 148774
    Prev
    Next
    INDEX
    Explanations

    defamation and legal trials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     Gant
    0.75
     treaty
    0.72
     রাজশাহী
    0.70
    ogenies
    0.70
     Egan
    0.70
     whey
    0.70
    Milwaukee
    0.69
    닭
    0.69
     Treaty
    0.69
     Holstein
    0.67
    POSITIVE LOGITS
     Depp
    1.72
     Johnny
    1.40
    Johnny
    1.38
     Heard
    1.10
    Pir
    1.08
     defam
    1.02
     Pirates
    1.02
     def
    1.01
     Pirate
    0.98
     Def
    0.95
    Activations Density 0.007%

    No Known Activations