© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 203713
    Prev
    Next
    INDEX
    Explanations

    military domination, chatbot interfaces, economic indicators, drive performance

    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
     disag
    0.52
     Slovens
    0.46
    Mexico
    0.45
     SeekBar
    0.45
    followlike
    0.44
     Statistik
    0.44
    𝖙
    0.44
    जेंडर
    0.43
    Чем
    0.43
    氬
    0.43
    POSITIVE LOGITS
     acronym
    0.41
     globular
    0.39
     utilises
    0.39
     அப்பா
    0.39
     си
    0.38
     rotating
    0.38
     rips
    0.38
     reversible
    0.38
     없다
    0.38
    早已
    0.38
    Activations Density 0.005%

    No Known Activations