© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11130
    Prev
    Next
    INDEX
    Explanations

    Jungkook kidnapped wedding hospital

    np_acts-logits-general · gemini-2.5-flash-lite

    describing emotional states and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     langfrist
    0.54
     implementação
    0.47
     nutzen
    0.46
     সংখ্য
    0.45
     внед
    0.45
     கட்டமை
    0.45
     diferenciar
    0.44
    儼
    0.44
     verwenden
    0.44
     definir
    0.43
    POSITIVE LOGITS
     Jungkook
    0.45
     继续
    0.44
     kissed
    0.40
     R
    0.40
     kidn
    0.38
     night
    0.38
     wedding
    0.38
     princess
    0.37
     kidnapped
    0.37
     hospital
    0.37
    Activations Density 0.436%

    No Known Activations